© 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. 11541
    Prev
    Next
    INDEX
    Explanations

    im followed by certain words

    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
     getValue
    2.94
    Ⓐ
    2.92
     glycos
    2.89
     removeFrom
    2.86
     scrape
    2.86
    𒁺
    2.74
    ☠
    2.70
     zal
    2.69
     ceded
    2.65
    큰
    2.64
    POSITIVE LOGITS
    mersive
    3.76
    ्युनिटी
    3.32
    ágenes
    3.08
    ми
    2.93
    zenie
    2.80
    تص
    2.80
    %%
    2.75
    FlatStyle
    2.74
    ición
    2.71
    нии
    2.69
    Activations Density 0.084%

    No Known Activations