© 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. 238153
    Prev
    Next
    INDEX
    Explanations

    analysis, screen, released, filled, block

    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
    कल्प
    0.45
    ście
    0.43
     Beads
    0.42
     تشکیل
    0.42
    月に
    0.40
     almış
    0.40
    蕃
    0.40
    ㄜ
    0.40
     brou
    0.40
    तिथि
    0.39
    POSITIVE LOGITS
     границ
    0.59
    0
    0.53
     края
    0.52
     antigos
    0.50
     miles
    0.47
    slüman
    0.47
    outheast
    0.46
     Уен
    0.46
     Grenze
    0.45
     antiguo
    0.45
    Activations Density 0.000%

    No Known Activations