© 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. 61759
    Prev
    Next
    INDEX
    Explanations

    other sectors

    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
    RuL
    0.53
    ни
    0.52
     шуда
    0.51
    ◤
    0.50
    𒋛
    0.48
    addena
    0.48
    غول
    0.47
     regra
    0.47
    ڈن
    0.47
    眩
    0.47
    POSITIVE LOGITS
     with
    0.53
    ities
    0.47
     communities
    0.46
     Corner
    0.45
    ience
    0.45
    ings
    0.45
     activity
    0.44
     institutional
    0.44
     Quarter
    0.44
     vineyards
    0.43
    Activations Density 0.005%

    No Known Activations