© 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. 83383
    Prev
    Next
    INDEX
    Explanations

    achievable price, Bart has, requested photos

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

    down, returns, lost

    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
     apresentar
    0.53
     преподава
    0.51
    ফ
    0.47
     yüksek
    0.47
    ędzynarod
    0.46
     Alicia
    0.46
     playerName
    0.46
     apresent
    0.45
     automakers
    0.45
     μεγαλ
    0.45
    POSITIVE LOGITS
     ティ
    0.45
    wider
    0.43
    FRAMERATE
    0.43
    SAA
    0.42
    ◟
    0.41
    ை
    0.41
    metal
    0.40
    IBRARY
    0.40
    putted
    0.40
    ITAS
    0.40
    Activations Density 0.002%

    No Known Activations