© 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. 78656
    Prev
    Next
    INDEX
    Explanations

    if applicable

    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
     suppos
    -1.14
    TokenNameEQUAL
    -0.93
    Expedia
    -0.92
     ressemb
    -0.91
     CERTAIN
    -0.90
     verboten
    -0.89
    isSame
    -0.89
    TestBase
    -0.88
    儚
    -0.88
     RECOMMENDED
    -0.88
    POSITIVE LOGITS
     applicable
    5.03
     relevant
    3.31
    applicable
    3.14
     appropriate
    2.92
     Applicable
    2.84
    Applicable
    2.72
     APPLICABLE
    2.55
    relevant
    2.17
     applies
    2.09
     pertinent
    2.03
    Activations Density 0.030%

    No Known Activations