© 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. 62067
    Prev
    Next
    INDEX
    Explanations

    word followed by descriptor

    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
    酈
    0.52
     sphinct
    0.46
    긍
    0.46
     innervation
    0.45
    ALITY
    0.43
     utilizzo
    0.42
    ល់
    0.42
    URACY
    0.41
    在家
    0.41
    ज्ञा
    0.41
    POSITIVE LOGITS
    let
    0.45
    m
    0.42
    rester
    0.42
     Skype
    0.41
    self
    0.41
     Europa
    0.41
     them
    0.40
     Mari
    0.40
     Hamburg
    0.39
     better
    0.39
    Activations Density 0.010%

    No Known Activations