© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66862
    Prev
    Next
    INDEX
    Explanations

    states or conditions described

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

    The neuron responds to positive evaluative adjectives or adverbs that signal things being good, correct, normal, or satisfactory.

    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
     član
    -0.91
    otry
    -0.89
    Quiénes
    -0.85
    ел
    -0.85
     cilvē
    -0.84
     līdz
    -0.84
    vember
    -0.81
    yel
    -0.81
    alda
    -0.80
    Cuánt
    -0.77
    POSITIVE LOGITS
     but
    1.15
    unlike
    0.92
    except
    0.84
     следующий
    0.83
    輸
    0.82
     ورزشی
    0.79
     flesta
    0.79
    ～」
    0.78
    Neden
    0.78
     tuer
    0.77
    Activations Density 0.142%

    No Known Activations