© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3154
    Prev
    Next
    INDEX
    Explanations

    2. step

    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_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
     [*
    0.94
     /-
    0.91
     ✅
    0.91
     *$
    0.89
     -,
    0.88
     [_
    0.88
     ✔
    0.85
     hairst
    0.85
     ▶
    0.85
    <0x84>
    0.85
    POSITIVE LOGITS
    First
    0.79
    Important
    0.77
    Pop
    0.76
    Those
    0.74
    在
    0.72
    Again
    0.72
    esempio
    0.71
    Step
    0.69
    Example
    0.68
    =
    0.67
    Activations Density 0.797%

    No Known Activations