© 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. 41088
    Prev
    Next
    INDEX
    Explanations

    Stability and instability concepts

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

    financial abuse

    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
     Ibid
    0.42
     j
    0.40
    nome
    0.39
     proiz
    0.39
     also
    0.38
    vell
    0.38
    Ibid
    0.38
     ۔
    0.37
     .
    0.37
     منہ
    0.37
    POSITIVE LOGITS
     লিঙ্ক
    0.44
     Stability
    0.40
    ;%(
    0.40
    UAWEI
    0.39
     stability
    0.39
     instability
    0.39
    ResponseWriter
    0.38
     DECL
    0.38
    Ꮈ
    0.38
     instabilities
    0.38
    Activations Density 0.012%

    No Known Activations