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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82725
    Prev
    Next
    INDEX
    Explanations

    syntax for structure access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.37
     like
    -1.25
     for
    -1.13
     if
    -1.13
     that
    -1.09
     to
    -1.06
    :
    -1.03
     also
    -1.02
     but
    -0.99
     with
    -0.97
    POSITIVE LOGITS
     _,
    2.14
    _,
    1.66
    ~,
    1.45
    __,
    1.34
     basura
    1.20
     llave
    1.10
     baixar
    1.10
     acier
    1.06
     secuen
    1.03
    junk
    1.02
    Activations Density 0.007%

    No Known Activations