© 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. 193260
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbsproject familyobserved numbersthese types of words

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

    physical measurements and objects

    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
     우리는
    0.46
    ウンド
    0.45
    ).*
    0.45
     tendremos
    0.45
     morrer
    0.45
     wszyst
    0.44
     میرے
    0.44
     mindig
    0.44
    ╋
    0.44
     зу
    0.44
    POSITIVE LOGITS
    HAV
    0.48
     HA
    0.46
     கொண்டார்
    0.46
    ΩΝ
    0.46
     EMAIL
    0.45
    hal
    0.44
     FF
    0.44
    ㇂
    0.43
    INAL
    0.42
    EMAIL
    0.42
    Activations Density 0.000%

    No Known Activations