© 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. 224813
    Prev
    Next
    INDEX
    Explanations

    legal or claim language

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

    inspection procedures

    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
    Barrier
    0.46
    𝑉
    0.43
    人体
    0.43
    区间
    0.43
    Theta
    0.42
    чем
    0.42
    ۹
    0.42
    㻁
    0.42
    Comb
    0.42
    ThreadGroup
    0.41
    POSITIVE LOGITS
     निगरानी
    0.54
    on
    0.51
    enzel
    0.49
    िलास
    0.47
     praw
    0.47
    ्याज
    0.46
    hik
    0.46
     anglais
    0.46
     penyeleng
    0.46
    hra
    0.46
    Activations Density 0.000%

    No Known Activations