Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53013
    Prev
    Next
    INDEX
    Explanations

    u to verb

    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_29_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
    firma
    1.09
    㤈
    1.01
    ের
    0.96
     ditth
    0.96
    นาน
    0.94
    湎
    0.94
    佢
    0.93
     इत्या
    0.92
    spectral
    0.92
    pup
    0.91
    POSITIVE LOGITS
     r
    1.37
    pping
    1.17
     R
    0.93
     Will
    0.91
    gh
    0.89
     derive
    0.85
     realize
    0.84
     can
    0.84
     Ou
    0.81
     ر
    0.80
    Activations Density 0.002%

    No Known Activations