© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77814
    Prev
    Next
    INDEX
    Explanations

    start of listing or date

    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
     without
    -1.38
     and
    -1.35
     to
    -1.34
     for
    -1.34
     when
    -1.30
     with
    -1.10
     by
    -1.10
     after
    -1.08
     informaci
    -1.04
     before
    -1.01
    POSITIVE LOGITS
    \_
    1.43
    ();
    1.27
    _,
    1.23
    ();
    
    1.22
    ().
    1.19
    _
    1.18
    _;
    1.17
    »,
    1.17
    (),
    1.16
     (_
    1.16
    Activations Density 0.004%

    No Known Activations