© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20681
    Prev
    Next
    INDEX
    Explanations

    overwriting existing values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    valmentaja
    0.44
     azok
    0.43
     mohli
    0.42
    我
    0.41
     двер
    0.41
    大家
    0.41
    ផុត
    0.40
     couldnt
    0.39
    食物
    0.39
     我
    0.39
    POSITIVE LOGITS
     fade
    0.42
     bew
    0.40
     fluctuations
    0.39
     misalignment
    0.39
     embezzlement
    0.38
    ную
    0.38
     throttling
    0.38
     compressibility
    0.38
     locality
    0.37
    เสีย
    0.37
    Activations Density 0.001%

    No Known Activations