© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2261
    Prev
    Next
    INDEX
    Explanations

    underscores followed by identifiers

    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_17_width_16k_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
    {}".
    2.76
    я
    2.72
    {}'.
    2.67
    и
    2.57
    कोर्ट
    2.32
    া
    2.22
    et
    2.22
     Torque
    2.21
    ного
    2.20
    {{
    2.13
    POSITIVE LOGITS
    Bismillahirrah
    2.78
    gaxModule
    2.67
    _{
    2.60
    ''_
    2.44
    -_
    2.36
    teil
    2.35
    '_
    2.30
    MSFontService
    2.22
    -_-
    2.18
    putchar
    2.13
    Activations Density 0.127%

    No Known Activations