© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47480
    Prev
    Next
    INDEX
    Explanations

    how closely

    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
     आम्हाला
    0.43
    PR
    0.40
     మరియు
    0.40
    âge
    0.39
    听
    0.39
     depictions
    0.39
     unapolog
    0.38
    DC
    0.38
    ótico
    0.38
     interi
    0.38
    POSITIVE LOGITS
     Sli
    0.44
    Klein
    0.43
     chiese
    0.41
     ከአ
    0.41
     getUserBy
    0.39
     Ні
    0.39
     小
    0.38
     Ці
    0.38
     سے
    0.38
     дели
    0.38
    Activations Density 0.016%

    No Known Activations