© 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. 2112
    Prev
    Next
    INDEX
    Explanations

    video analysis, tutorials, interviews, editing

    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
    te
    2.87
    ش
    2.56
    ina
    2.53
    therly
    2.50
     worry
    2.47
    }";
    2.45
    سون
    2.45
    ttet
    2.45
    }'.
    2.43
     inclined
    2.41
    POSITIVE LOGITS
    ا
    3.13
    𝐥
    3.06
    ء
    3.00
     możliwe
    2.89
    𝐫
    2.87
    le
    2.81
     Neem
    2.75
    𝐚
    2.74
    𝐝
    2.73
    েও
    2.73
    Activations Density 0.207%

    No Known Activations