© 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. 25506
    Prev
    Next
    INDEX
    Explanations

    deal with

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

    looking for True/IF conditions

    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
     Fleurit
    0.53
     equivoc
    0.50
    숴
    0.49
    不住
    0.45
     Treated
    0.45
     Моло
    0.44
     treated
    0.43
    '`--'`--
    0.43
     Silva
    0.43
    кратно
    0.42
    POSITIVE LOGITS
    ác
    0.51
    ery
    0.49
    ene
    0.48
    ER
    0.48
    ENE
    0.48
    ase
    0.47
    ules
    0.46
    写入
    0.46
     solicitud
    0.46
    write
    0.46
    Activations Density 0.000%

    No Known Activations