© 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. 77956
    Prev
    Next
    INDEX
    Explanations

    Arm prefix

    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
    區
    -0.84
     zgod
    -0.80
    ñera
    -0.75
     odm
    -0.74
    φ
    -0.72
     wiadomo
    -0.72
     Rainbow
    -0.71
    大統領
    -0.71
    President
    -0.70
     knapp
    -0.70
    POSITIVE LOGITS
    arium
    1.02
     Arma
    0.97
     arma
    0.89
     armar
    0.84
    arma
    0.82
    dillo
    0.79
    geddon
    0.78
     Arme
    0.78
     Arm
    0.76
     Pries
    0.75
    Activations Density 0.019%

    No Known Activations