© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14213
    Prev
    Next
    INDEX
    Explanations

    rely on, depending on, remains fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     Gesetz
    1.70
     Assim
    1.62
     Kalian
    1.48
     Embr
    1.48
     Karriere
    1.45
    ,|
    1.45
     secreto
    1.45
     dreamer
    1.44
     Counting
    1.44
     Menschen
    1.43
    POSITIVE LOGITS
    дыду
    1.22
    ached
    1.22
    ownie
    1.18
    ใ
    1.16
    irà
    1.12
    branded
    1.11
    }_{-}\
    1.10
    enumi
    1.07
    都已经
    1.06
    询
    1.05
    Activations Density 0.000%

    No Known Activations