© 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-65K
    7. 45016
    Prev
    Next
    INDEX
    Explanations

    food, egg, Sun, land, banana

    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_65k_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
     VARCHAR
    0.44
    ੍ਰ
    0.42
    adrenergic
    0.41
     จำ
    0.39
     വ്യ
    0.38
    irradiated
    0.38
     "'.$
    0.37
    す
    0.37
    strength
    0.37
     thân
    0.37
    POSITIVE LOGITS
     بينا
    0.55
     ermöglicht
    0.44
     Musik
    0.44
    Basis
    0.43
     Zuf
    0.43
    Language
    0.43
    ملك
    0.42
     Projekt
    0.41
    Built
    0.41
    كلمنا
    0.41
    Activations Density 0.011%

    No Known Activations