© 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. 223669
    Prev
    Next
    INDEX
    Explanations

    hunting seasons

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

    personal and explicitly stated information

    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
    𝘼
    0.46
    年至
    0.45
     linha
    0.44
    部門
    0.44
    一下
    0.43
    𝙘
    0.43
     principalTable
    0.43
    啊
    0.41
    cosx
    0.40
    將
    0.40
    POSITIVE LOGITS
     biore
    0.46
    inking
    0.45
     제조
    0.42
     tristeza
    0.42
     polystyrene
    0.41
    ِ
    0.41
     polos
    0.40
    transactions
    0.40
     Machado
    0.40
     بر
    0.40
    Activations Density 0.000%

    No Known Activations