© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11492
    Prev
    Next
    INDEX
    Explanations

    following

    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
     playthrough
    0.72
     근데
    0.72
    ).</
    0.70
     soldering
    0.69
     however
    0.68
    UseVisualStyle
    0.67
     reliance
    0.66
     pinch
    0.65
     dispensing
    0.65
    ただし
    0.65
    POSITIVE LOGITS
    ("""
    1.15
    如下
    1.14
    以下
    1.08
    ('''
    1.01
    following
    0.95
    ({
    0.94
    Following
    0.94
     berikut
    0.92
     seguente
    0.91
    以下の
    0.90
    Activations Density 0.222%

    No Known Activations