© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9200
    Prev
    Next
    INDEX
    Explanations

    places like Reef Village

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

    words ending in abstract suffixes

    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_40_width_16k_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
    ্বরূপ
    0.46
     ::=
    0.44
     связь
    0.43
     инвали
    0.43
    низ
    0.42
     fornisce
    0.42
    tte
    0.42
     помнить
    0.42
    šnji
    0.41
     fornire
    0.40
    POSITIVE LOGITS
    ooka
    0.53
    iness
    0.53
    EEK
    0.46
    zaam
    0.46
    ੂ
    0.46
    iese
    0.46
    laid
    0.46
    ies
    0.45
    पात
    0.45
    ू
    0.45
    Activations Density 0.936%

    No Known Activations