© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    use it

    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
     useful
    2.31
    тың
    2.16
    ▫
    2.15
    и
    2.10
     числе
    2.04
     abiding
    1.98
     нужно
    1.96
    טים
    1.96
     suited
    1.95
     dob
    1.93
    POSITIVE LOGITS
    fully
    2.47
     sparingly
    2.37
    zame
    2.20
    RA
    2.10
    fulness
    2.06
     '\\;'
    2.05
     Tapatalk
    1.93
    inand
    1.93
    ून
    1.91
    िता
    1.90
    Activations Density 0.509%

    No Known Activations