© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 48201
    Prev
    Next
    INDEX
    Explanations

    intercept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    Collapse
    0.45
    樎
    0.41
     covalently
    0.40
    Desk
    0.40
    㐬
    0.40
     carinatis
    0.39
     Disorder
    0.39
     சுத்தம்
    0.38
    torio
    0.38
    解消
    0.38
    POSITIVE LOGITS
     intercept
    3.75
     intercepts
    3.50
    intercept
    3.34
     interception
    3.34
    Intercept
    3.28
     intercepted
    3.27
     interceptions
    2.92
    拦截
    2.84
    Interceptor
    2.52
    攔
    2.08
    Activations Density 0.018%

    No Known Activations