© 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. 58441
    Prev
    Next
    INDEX
    Explanations

    credit card

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

    right pane, doctors arrived, Songsmiths, Spell Fragments, ambition hung

    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
     मियां
    0.53
    дной
    0.52
     सचिवा
    0.52
     pedibusque
    0.49
     рабочего
    0.49
    𝘭
    0.49
     председа
    0.49
     जिसको
    0.48
    <unused42>
    0.48
     régions
    0.48
    POSITIVE LOGITS
     style
    0.52
     STYLE
    0.52
     C
    0.50
     Style
    0.50
     R
    0.50
     r
    0.49
     ONLY
    0.48
    0
    0.48
     X
    0.47
     K
    0.47
    Activations Density 0.000%

    No Known Activations