© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2510
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions or processes

    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_9_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
    titan
    3.18
     hordes
    3.00
    lays
    2.93
    oncesto
    2.89
    t
    2.81
    tedir
    2.80
    рные
    2.70
    typical
    2.69
     pivoted
    2.69
    দের
    2.67
    POSITIVE LOGITS
    ه
    3.70
    o
    3.18
     ulter
    2.66
     번째
    2.64
    岃
    2.55
     amely
    2.52
    இவ்வாறு
    2.52
     prosecution
    2.52
    屽
    2.41
    áculo
    2.40
    Activations Density 0.142%

    No Known Activations