© 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. 76438
    Prev
    Next
    INDEX
    Explanations

    numbers assigned

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

    context-free or context-aware

    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
     হাইড্রোক
    0.47
    </thead>
    0.44
     hydrochloric
    0.43
    おります
    0.42
     hydrogen
    0.42
    blogspot
    0.41
     isoniazid
    0.41
    adou
    0.41
    ிருக்கும்
    0.41
     reasonably
    0.41
    POSITIVE LOGITS
    æ
    0.50
     município
    0.49
    ті
    0.48
    }^{-}\
    0.47
    ార్
    0.47
    🇳
    0.47
    }^{*}$
    0.47
    ă
    0.46
     einzigen
    0.45
     começando
    0.45
    Activations Density 0.000%

    No Known Activations