© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 10225
    Prev
    Next
    INDEX
    Explanations

    Code, test, association, choice, contact, bus

    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
    \,\
    1.30
     inferences
    1.26
    ])),
    1.24
    \,.
    1.23
     endowed
    1.22
    '};
    1.22
    其
    1.22
     Ow
    1.20
    References
    1.17
    ডেইলি
    1.16
    POSITIVE LOGITS
    ter
    1.37
    ह
    1.35
     やつ
    1.31
    હ
    1.28
    يب
    1.27
    גים
    1.26
    ﯽ
    1.25
    ﻲ
    1.24
    ็ว
    1.24
    ั่ง
    1.24
    Activations Density 0.000%

    No Known Activations