© 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. 92115
    Prev
    Next
    INDEX
    Explanations

    family or person by number

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

    identify skills and systems

    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
    ຕິດຕໍ່
    0.46
     ሂ
    0.44
     αντί
    0.43
     मध्या
    0.43
     flore
    0.43
    थरूम
    0.43
    Dimethyl
    0.42
    ຜະລ
    0.42
     atento
    0.42
     próprias
    0.41
    POSITIVE LOGITS
    ങ്ങ്
    0.54
    crew
    0.45
    oine
    0.44
     DIN
    0.44
    y
    0.44
    panda
    0.43
     चाहर
    0.43
    fz
    0.43
     домаћин
    0.43
    <0x96>
    0.42
    Activations Density 0.000%

    No Known Activations