© 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. 75252
    Prev
    Next
    INDEX
    Explanations

    critical communications

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

    parental rights and support

    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
     Hanna
    0.50
     elektry
    0.50
     Greenville
    0.49
     Bader
    0.47
     Electric
    0.46
     Scribner
    0.46
    C
    0.46
     मांसपेशियों
    0.45
     বৈদ্য
    0.45
     Denton
    0.44
    POSITIVE LOGITS
    ༣
    0.53
     coexistence
    0.49
     catálogo
    0.48
    ెండు
    0.45
    டுப
    0.45
     incompar
    0.45
    半島
    0.45
    🆔
    0.45
     ruso
    0.45
     polémica
    0.45
    Activations Density 0.000%

    No Known Activations