© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    driving force

    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
    ाई
    3.41
    u
    3.32
    ીએ
    3.27
    ાર્
    2.82
    ामध्ये
    2.79
    schaft
    2.76
    нибудь
    2.75
     beryllium
    2.66
    াটো
    2.63
    л
    2.62
    POSITIVE LOGITS
    ح
    2.99
     piston
    2.94
     hac
    2.89
    в
    2.81
    ن
    2.80
    ուր
    2.75
    서
    2.75
    นี้
    2.68
    که
    2.66
     Scream
    2.62
    Activations Density 0.213%

    No Known Activations