© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66016
    Prev
    Next
    INDEX
    Explanations

    values and concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on semantically rich content words (i.e. infrequent, informative keywords) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------
    -1.02
    Pengertian
    -1.01
     iphone
    -1.00
    thail
    -0.93
    いたしました
    -0.90
    PATRICK
    -0.90
    скать
    -0.90
    Penjelasan
    -0.88
    Inhalts
    -0.88
     poquito
    -0.88
    POSITIVE LOGITS
    },
    0.95
    hancers
    0.89
    umenti
    0.85
     Bonuses
    0.85
    тивное
    0.83
    请问
    0.81
    minus
    0.80
     confuso
    0.80
    >';
    0.80
     InputMaybe
    0.79
    Activations Density 0.111%

    No Known Activations