© 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. 200667
    Prev
    Next
    INDEX
    Explanations

    after 'to' or 'Hero'

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

    common conjunctions and discourse markers

    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
    naked
    0.49
    n
    0.48
    á
    0.47
    ഴിഞ്ഞ
    0.47
     Naked
    0.45
    नल
    0.45
    unsubscribe
    0.44
    Expires
    0.44
    亽
    0.44
    antha
    0.43
    POSITIVE LOGITS
     creations
    0.55
     collège
    0.48
     resonated
    0.46
     carcinogenesis
    0.46
     Allgemeine
    0.46
     resonates
    0.46
     acoust
    0.45
     (“
    0.44
     Rosen
    0.44
     piers
    0.44
    Activations Density 0.000%

    No Known Activations