© 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. 12053
    Prev
    Next
    INDEX
    Explanations

    below is

    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
    のは
    3.60
    и
    3.46
    ীর
    3.38
    링
    3.20
    laş
    3.10
     ∗
    3.00
    𝘶
    2.93
    𝐭
    2.91
    uates
    2.77
    おり
    2.76
    POSITIVE LOGITS
     reproach
    3.46
    mentioned
    3.21
    decks
    3.13
    ground
    2.82
    न
    2.80
    ्याय
    2.73
    TextViewStyle
    2.73
    ්
    2.70
    tower
    2.67
    pounds
    2.66
    Activations Density 0.029%

    No Known Activations