© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188715
    Prev
    Next
    INDEX
    Explanations

    microwave high, ATR crystal, energy densities

    np_acts-logits-general · gemini-2.5-flash-lite

    Penn, lei, God, PCI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝚗
    0.53
    et
    0.51
     financially
    0.49
     tratado
    0.49
    lerce
    0.48
     collars
    0.47
     ঘাঁটি
    0.47
     cinqui
    0.47
    UserProg
    0.46
    Touches
    0.46
    POSITIVE LOGITS
    \{
    0.53
    ACA
    0.49
    ADA
    0.46
    ت
    0.46
    你可以
    0.46
    ANCH
    0.46
    ח
    0.46
    AC
    0.45
    CHARGE
    0.45
     Cholesterol
    0.45
    Activations Density 0.000%

    No Known Activations