© 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. 74869
    Prev
    Next
    INDEX
    Explanations

    our possessions and identity

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

    polar bears found

    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
     artefacts
    0.50
    혔
    0.49
     cytokines
    0.45
     سفید
    0.45
    י
    0.45
    ।"
    0.44
     dame
    0.44
    สิ่งที่
    0.44
    ਸ
    0.44
     reprises
    0.43
    POSITIVE LOGITS
    遴
    0.50
     Worldwide
    0.46
    ě
    0.43
    opol
    0.43
     Coalition
    0.42
    উঠ
    0.42
    欄
    0.42
    of
    0.42
     Zag
    0.42
     Archiv
    0.41
    Activations Density 0.000%

    No Known Activations