© 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. 220257
    Prev
    Next
    INDEX
    Explanations

    builders do, two congruent, primarily intended

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

    black markets, illegal activity, eternity

    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
     Año
    0.50
    HH
    0.50
    на
    0.49
    または
    0.49
     Při
    0.48
    SH
    0.47
    H
    0.46
    مہ
    0.45
    İL
    0.45
    ità
    0.44
    POSITIVE LOGITS
     asemenea
    0.47
    assapi
    0.45
     metabolism
    0.45
    ле
    0.43
    வையும்
    0.41
     ఐ
    0.41
     metabolized
    0.41
     साम्राज्य
    0.41
     पीने
    0.40
    ើន
    0.40
    Activations Density 0.000%

    No Known Activations