© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2812
    Prev
    Next
    INDEX
    Explanations

    punctuation after lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     "+"
    0.65
     Cooper
    0.65
     Nxa
    0.63
     Trevor
    0.63
     Uni
    0.62
     Bell
    0.61
     Global
    0.61
    য়ী
    0.61
    ⽤
    0.61
     BUN
    0.59
    POSITIVE LOGITS
    .,
    3.35
    .;
    2.66
    .,"
    2.54
    .:
    2.37
    .),
    2.26
    ..,
    2.20
    ।,
    2.11
     .,
    2.10
    }$.,
    2.05
    。,
    1.99
    Activations Density 0.300%

    No Known Activations