© 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. 203033
    Prev
    Next
    INDEX
    Explanations

    prophecy and announcements

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

    converting text, video length, statistics value

    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
    Sum
    0.46
    㳡
    0.45
    োলন
    0.44
    INSON
    0.44
     zwr
    0.43
    Der
    0.43
    渽
    0.43
    SSF
    0.43
     sourceL
    0.42
    媤
    0.42
    POSITIVE LOGITS
     marvellous
    0.54
     prophe
    0.50
     decept
    0.47
    ätz
    0.47
     marvelous
    0.46
    éi
    0.46
     prodigious
    0.46
     prophetic
    0.45
     apostolic
    0.45
     prophes
    0.45
    Activations Density 0.000%

    No Known Activations