© 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. 196756
    Prev
    Next
    INDEX
    Explanations

    protect against

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

    philosophical statements about reality

    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
     ODBC
    0.50
     megsz
    0.48
     finner
    0.46
    驩
    0.46
     zd
    0.46
    फ्रेंस
    0.44
     reciprocal
    0.43
     Zara
    0.43
     hver
    0.42
    উর
    0.42
    POSITIVE LOGITS
    <0x0D>
    0.55
     حي
    0.49
    あい
    0.46
    もちろん
    0.45
     tránsito
    0.45
     प्रव
    0.44
     کاروب
    0.44
    幼稚
    0.43
     цик
    0.43
    NEE
    0.43
    Activations Density 0.000%

    No Known Activations