© 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. 62650
    Prev
    Next
    INDEX
    Explanations

    still cool, five years, more positive

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

    exceptions, conditions, or negations

    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
     छन्
    0.45
    INGS
    0.43
     ['(?
    0.42
     發
    0.42
     ऐप्स
    0.41
    ECH
    0.40
    ^
    0.40
    向け
    0.40
     appreciated
    0.39
    ARG
    0.39
    POSITIVE LOGITS
     bukanlah
    0.60
     bukan
    0.58
     tidak
    0.55
     wasn
    0.54
    还没有
    0.52
     ikke
    0.51
     pertandingan
    0.50
    还不
    0.50
     unap
    0.49
     misschien
    0.48
    Activations Density 0.000%

    No Known Activations