© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15035
    Prev
    Next
    INDEX
    Explanations

    defining properties or methods

    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_22_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
    ोम
    1.20
    و
    1.18
     फरार
    1.17
     девушка
    1.16
    িন
    1.13
    ينا
    1.12
     vêtements
    1.11
     चलता
    1.09
    ңыз
    1.08
    дини
    1.08
    POSITIVE LOGITS
    I
    0.90
     demonstrating
    0.86
     Presumably
    0.85
     pensar
    0.84
     details
    0.83
     desiring
    0.82
    要求
    0.82
     opportunities
    0.81
     technically
    0.81
     Demonstrate
    0.80
    Activations Density 0.000%

    No Known Activations