© 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. 34332
    Prev
    Next
    INDEX
    Explanations

    singing in front of people

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

    past, last, increased, change, sentiment

    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
    Ap
    0.51
    Описание
    0.46
     jot
    0.46
    リリース
    0.44
    桁
    0.43
     начина
    0.43
     Fonbet
    0.43
     sherry
    0.43
     nationalities
    0.42
    。)
    0.42
    POSITIVE LOGITS
    epte
    0.44
    ellan
    0.43
     сега
    0.42
    æs
    0.42
    ains
    0.42
    <0x00>
    0.42
     সোমবার
    0.40
     partenaires
    0.39
     úgy
    0.39
     месе
    0.39
    Activations Density 0.000%

    No Known Activations