© 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-262K
    7. 10708
    Prev
    Next
    INDEX
    Explanations

    specific letter counts

    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_262k_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
    biet
    1.83
    cInfo
    1.69
    bate
    1.63
    vate
    1.59
    𝒑
    1.58
    uem
    1.57
     Posterior
    1.57
    至于
    1.56
     laget
    1.56
    ักษณะ
    1.55
    POSITIVE LOGITS
    н
    2.01
    }=\
    1.70
    ה
    1.69
    en
    1.64
    یان
    1.62
    يًا
    1.47
    세계
    1.46
    জীবনে
    1.45
    PD
    1.44
    ة
    1.44
    Activations Density 0.000%

    No Known Activations