© 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. 31325
    Prev
    Next
    INDEX
    Explanations

    citation, and locations

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

    citadel fortress

    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
     membahas
    0.44
     любом
    0.42
     wcout
    0.42
     чём
    0.42
     yaklaş
    0.41
     wybra
    0.41
    吣
    0.41
     نگه
    0.41
     разговор
    0.41
     दुल्हन
    0.39
    POSITIVE LOGITS
    header
    0.47
    quiries
    0.45
    shader
    0.44
     Provincial
    0.43
    queries
    0.43
    simple
    0.42
    my
    0.41
    R
    0.41
     European
    0.40
    0
    0.40
    Activations Density 0.001%

    No Known Activations