© 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. 10-GEMMASCOPE-RES-131K
    7. 73876
    Prev
    Next
    INDEX
    Explanations

    who followed by needs or actions

    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_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
     they
    -1.55
    Продам
    -1.48
     cantora
    -1.46
     atriz
    -1.40
     about
    -1.38
    㩒
    -1.37
    Ruju
    -1.37
    pagest
    -1.36
     皇族
    -1.34
    продам
    -1.33
    POSITIVE LOGITS
     know
    1.84
    それを
    1.59
    :]:
    1.44
     ",
    1.44
    +"&
    1.41
     sein
    1.40
    gbarkeit
    1.40
    能不能
    1.39
     want
    1.39
     have
    1.39
    Activations Density 0.036%

    No Known Activations