© 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. 34-GEMMASCOPE-RES-131K
    7. 78476
    Prev
    Next
    INDEX
    Explanations

    so many or much

    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
    such
    -1.18
    әһ
    -1.18
    quite
    -1.06
    particularly
    -1.02
    longer
    -1.01
     tylko
    -0.99
    further
    -0.99
    olog
    -0.98
    previously
    -0.92
    stuffs
    -0.92
    POSITIVE LOGITS
     many
    1.58
     much
    1.57
     многих
    1.20
     viele
    1.20
    Many
    1.14
    makeat
    0.92
     mnoho
    0.91
     why
    0.90
     Many
    0.90
    attere
    0.90
    Activations Density 0.030%

    No Known Activations