© 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. 4179
    Prev
    Next
    INDEX
    Explanations

    promises and assurances

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

    communicated, recommendation, attending, join

    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
    雜
    0.50
     پژوه
    0.47
    雑
    0.46
    技能
    0.43
    しばらく
    0.42
    ູບ
    0.42
    ː
    0.41
    ImportGroup
    0.40
    ~\
    0.40
    期刊
    0.40
    POSITIVE LOGITS
     overruling
    0.56
     personally
    0.54
     unquestionably
    0.54
     personalmente
    0.53
     trusted
    0.53
     shockingly
    0.52
     obviamente
    0.51
     persönlich
    0.51
     absolutamente
    0.51
     graciously
    0.50
    Activations Density 0.004%

    No Known Activations