© 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. 206197
    Prev
    Next
    INDEX
    Explanations

    mirror, silver, next post, going up

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

    electrolytes and minerals

    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
    ത്മ
    0.62
     cuidado
    0.51
    assertArg
    0.51
    ziła
    0.50
     mehrerer
    0.50
     множе
    0.49
    🧖
    0.48
     juht
    0.48
     حی
    0.47
    🏂
    0.47
    POSITIVE LOGITS
     on
    0.50
     rapping
    0.44
     soldering
    0.43
     Google
    0.43
     rolled
    0.43
     ranging
    0.43
     soldered
    0.43
     thickness
    0.42
     nomination
    0.42
     depending
    0.42
    Activations Density 0.000%

    No Known Activations