© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13991
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation

    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
     colleagues
    1.44
     rebirth
    1.39
     mentality
    1.36
    openai
    1.35
    𝒕
    1.33
     colleague
    1.33
    cvtColor
    1.31
     companionship
    1.29
     Jackman
    1.29
     protagonisti
    1.28
    POSITIVE LOGITS
    heid
    1.41
    ن
    1.31
    на
    1.29
    iation
    1.24
    نن
    1.20
    вання
    1.19
    வம்
    1.16
    الك
    1.15
    տ
    1.14
    ので
    1.14
    Activations Density 0.071%

    No Known Activations