© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1105
    Prev
    Next
    INDEX
    Explanations

    `not precisely`, comma-separated descriptions

    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_13_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
    alse
    1.02
    oubt
    1.02
    ifty
    1.02
    isal
    0.96
    igil
    0.96
    atud
    0.95
    .
    0.92
     jost
    0.90
    ijer
    0.89
    ali
    0.89
    POSITIVE LOGITS
     consequências
    1.83
     ipotesi
    1.61
     część
    1.59
     특집
    1.56
     mój
    1.52
     conséquences
    1.51
     chapitre
    1.48
     chiesa
    1.48
     édition
    1.47
     Ρ
    1.45
    Activations Density 0.614%

    No Known Activations