© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    punctuation and parenthetical instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ungefähr
    0.69
     underestimated
    0.67
     forhold
    0.66
    石头
    0.64
    }}{(
    0.61
     remind
    0.61
     mengaj
    0.61
     chăm
    0.60
     rappeler
    0.60
    question
    0.59
    POSITIVE LOGITS
    ቹ
    0.66
    inology
    0.65
    Sw
    0.65
     Viewing
    0.65
     óptica
    0.63
    atorics
    0.63
     příjem
    0.61
    שים
    0.61
     ማለት
    0.60
     دید
    0.59
    Activations Density 0.084%

    No Known Activations