© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    removing or deleting items

    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
    en
    3.00
    ే
    2.40
    ר
    2.37
    ر
    2.19
     dynamo
    2.08
    良好
    1.99
     rundt
    1.98
     rey
    1.96
    рования
    1.96
    те
    1.93
    POSITIVE LOGITS
    %%%%%%%%
    2.54
    tion
    2.31
     therefrom
    2.28
     voorz
    2.23
    tions
    2.20
    ++++
    2.16
    нные
    2.16
    tive
    2.14
    fhir
    2.12
    ++++++++
    2.09
    Activations Density 0.229%

    No Known Activations