© 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. 51979
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun, specific languages

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

    explaining outcomes concisely

    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
     عادة
    0.42
    lon
    0.40
     hassles
    0.40
    }$.)
    0.39
    ase
    0.39
    PCR
    0.38
     satisfactorily
    0.38
    ولوج
    0.38
    obutyl
    0.38
    лення
    0.38
    POSITIVE LOGITS
     svůj
    0.57
    你需要
    0.54
    ⚔
    0.48
     свой
    0.47
     své
    0.47
    你不
    0.47
     swój
    0.47
     своих
    0.47
     אך
    0.46
     основу
    0.46
    Activations Density 0.000%

    No Known Activations