© 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. 203620
    Prev
    Next
    INDEX
    Explanations

    statement of

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

    options and variety

    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
    ти
    0.68
    ди
    0.53
    ík
    0.51
    ૩
    0.50
     エン
    0.49
    б
    0.49
    ्त
    0.48
    ಗರ
    0.48
    ３
    0.47
    ８
    0.47
    POSITIVE LOGITS
     Collaborative
    0.50
     Kreat
    0.48
     Worked
    0.47
     kari
    0.46
     Schematic
    0.46
     abolition
    0.46
    应对
    0.44
     collaborative
    0.44
     Whole
    0.44
     Discrete
    0.44
    Activations Density 0.000%

    No Known Activations