© 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. 45269
    Prev
    Next
    INDEX
    Explanations

    polynomials and sequences

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

    polynomials and redirects

    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
    Transactions
    0.52
    Playing
    0.50
    Between
    0.49
    ED
    0.49
    Operating
    0.48
    เปลี่ยน
    0.46
    Apl
    0.46
    濟
    0.46
    SCALE
    0.46
    sexual
    0.45
    POSITIVE LOGITS
     mout
    0.48
     etat
    0.41
     guide
    0.40
     drafted
    0.40
    }]}
    0.39
     et
    0.38
     Polit
    0.38
     exporters
    0.38
     upfront
    0.38
     undertook
    0.38
    Activations Density 0.000%

    No Known Activations