© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117120
    Prev
    Next
    INDEX
    Explanations

    wall hanging storage

    np_acts-logits-general · gemini-2.5-flash-lite

    social interaction, advice, or confrontation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vät
    0.51
    🛵
    0.49
     väldigt
    0.47
     pierres
    0.45
     bathed
    0.45
     shockingly
    0.44
     खुशी
    0.44
     absurd
    0.43
     grooves
    0.43
     샤
    0.43
    POSITIVE LOGITS
    產
    0.49
    DD
    0.45
    FD
    0.45
    C
    0.44
    LD
    0.44
    弔
    0.43
     McKenzie
    0.43
     IG
    0.42
     United
    0.41
    IO
    0.41
    Activations Density 0.000%

    No Known Activations