© 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. 983
    Prev
    Next
    INDEX
    Explanations

    end of clause or sentence

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

    sentence endings and continuations

    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
    Attr
    0.20
     harmonization
    0.19
     mushrooms
    0.18
    方
    0.18
    XXX
    0.18
     summation
    0.18
    overline
    0.18
     demarcation
    0.17
     summary
    0.17
    }:
    0.17
    POSITIVE LOGITS
    ције
    0.21
     ജില്ലാ
    0.21
     الذين
    0.21
     Eğer
    0.21
    頑張
    0.21
    čių
    0.20
    蟶
    0.20
     ndị
    0.20
     William
    0.20
     سے
    0.19
    Activations Density 0.385%

    No Known Activations