© 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. 59988
    Prev
    Next
    INDEX
    Explanations

    crude oil into refining tank

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

    cryptography, challenges, tied, structure

    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
     Essentials
    0.55
     combustibles
    0.55
    ata
    0.53
     Pact
    0.51
     restantes
    0.48
     buổi
    0.47
    ][_
    0.47
     मृ
    0.46
     ProRes
    0.46
     Omnibus
    0.46
    POSITIVE LOGITS
    ECO
    0.43
    Weiss
    0.42
    Doll
    0.42
     clerk
    0.42
     ঢুকে
    0.42
    ెర
    0.42
    ྒྱ
    0.42
    ACTIVITY
    0.41
    ﻓ
    0.41
    িকাংশ
    0.40
    Activations Density 0.000%

    No Known Activations