© 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. 136698
    Prev
    Next
    INDEX
    Explanations

    describing page content

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

    presented as if

    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
    ício
    0.52
     الكبير
    0.49
     deletion
    0.46
     முதல்
    0.45
     έχει
    0.45
    整体
    0.44
    临
    0.43
    ível
    0.42
     cancellation
    0.42
    协同
    0.42
    POSITIVE LOGITS
     hona
    0.45
    ſ
    0.42
    ropoda
    0.42
     inhale
    0.42
     sofa
    0.40
    EK
    0.40
    қ
    0.40
     Rech
    0.40
    ukiy
    0.39
     attractive
    0.39
    Activations Density 0.000%

    No Known Activations