© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 11427
    Prev
    Next
    INDEX
    Explanations

    numbers 6, 7, about, candidate, f

    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
    σιμο
    1.28
    𝑝
    1.26
    oft
    1.24
    <&
    1.23
    对应
    1.20
    er
    1.19
    maks
    1.19
    ্স
    1.19
    ifornia
    1.18
    flight
    1.18
    POSITIVE LOGITS
     infestation
    1.50
     closely
    1.31
     compromiso
    1.29
    }$
    1.25
     crave
    1.24
     certamente
    1.24
     entusiasmo
    1.23
     crescimento
    1.22
    ㅠ
    1.20
    тельности
    1.20
    Activations Density 0.000%

    No Known Activations