© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    following prepositions and specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    fromDate
    1.07
     možete
    1.06
     أيضا
    1.06
    嘢
    1.05
    st
    1.05
     объекты
    1.04
     modificaciones
    1.03
    วัต
    1.03
    ことが
    1.02
    acidad
    1.02
    POSITIVE LOGITS
     tongue
    1.16
    யோ
    1.10
     December
    1.06
    ীণ
    1.05
    $-
    1.05
     July
    1.05
     October
    1.04
     November
    1.04
     seventies
    1.02
     osmotic
    1.02
    Activations Density 0.000%

    No Known Activations