© 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. 22023
    Prev
    Next
    INDEX
    Explanations

    playfully mischievous

    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
     bunnies
    0.51
     duis
    0.49
    ?.
    0.49
     (_,
    0.47
     действи
    0.45
     superman
    0.45
     bunny
    0.45
    ل
    0.45
     веще
    0.43
    л
    0.43
    POSITIVE LOGITS
    利
    0.47
    护
    0.46
     På
    0.43
    ោង
    0.43
     minimalistic
    0.43
    调整
    0.42
     minimalist
    0.41
    selt
    0.41
    operatively
    0.41
     halter
    0.41
    Activations Density 0.000%

    No Known Activations