© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41056
    Prev
    Next
    INDEX
    Explanations

    methods, solutions, types, products

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

    The neuron strongly activates on content-bearing nouns—especially abstract or thematic nouns like “solutions,” “methods,” “information,” “equipment,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Perhaps
    -1.94
    Only
    -1.89
    There
    -1.87
    If
    -1.81
    Even
    -1.80
    While
    -1.71
    With
    -1.66
     or
    -1.66
    After
    -1.66
    Without
    -1.64
    POSITIVE LOGITS
    ཥ
    1.69
     sekret
    1.44
     The
    1.41
    </em>
    1.41
    })$
    1.38
    }=
    1.37
     dokument
    1.37
     arbres
    1.36
     biblia
    1.34
    ização
    1.33
    Activations Density 0.071%

    No Known Activations