© 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. 153811
    Prev
    Next
    INDEX
    Explanations

    states, conditions, or actions

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

    short for

    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
    ス
    0.60
    が大
    0.54
    Bitcoin
    0.52
    Nd
    0.52
    pps
    0.51
    ル
    0.51
    import
    0.50
     ス
    0.50
    L
    0.50
    }+
    0.49
    POSITIVE LOGITS
     practitioner
    0.50
     excuse
    0.47
    衅
    0.45
     Woolf
    0.43
    τέ
    0.42
    那你
    0.42
    你应该
    0.41
     eyesight
    0.41
     indiqué
    0.40
     رہنما
    0.40
    Activations Density 0.001%

    No Known Activations