© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    suffix or compound word endings

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

    language identification and grammar

    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
    0.38
     The
    0.32
     This
    0.31
    un
    0.31
     flawed
    0.30
     were
    0.29
     horrific
    0.29
     horrifying
    0.29
     H
    0.29
     Hitler
    0.29
    POSITIVE LOGITS
    Beverungen
    0.32
    Isopropyl
    0.31
    pOt
    0.31
    用水
    0.29
    거나
    0.29
    会儿
    0.29
    壶
    0.28
    水的
    0.27
     brisket
    0.27
     rhizosphere
    0.27
    Activations Density 0.000%

    No Known Activations