© 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. 15885
    Prev
    Next
    INDEX
    Explanations

    `do not` or descriptive adjectives

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

    knowledge, lyric, informal, Runner

    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
    j
    0.53
     First
    0.47
     Mika
    0.43
    ंडर
    0.42
    m
    0.42
     J
    0.40
    Prob
    0.40
    et
    0.39
     Susana
    0.39
     first
    0.39
    POSITIVE LOGITS
    毉
    0.44
    ()<
    0.43
     erfüllt
    0.43
     余
    0.43
     europäischen
    0.42
    <()>
    0.42
    环节
    0.41
     собственно
    0.41
     системой
    0.41
     interrump
    0.40
    Activations Density 0.000%

    No Known Activations