© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29132
    Prev
    Next
    INDEX
    Explanations

    fall through cracks

    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_40_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
     уси
    0.39
     conjectures
    0.39
     imprison
    0.38
    bert
    0.36
     безо
    0.36
    alse
    0.35
    肅
    0.35
    reversed
    0.35
    ALSE
    0.34
    ]^{-
    0.34
    POSITIVE LOGITS
     loophole
    1.02
     loopholes
    1.00
     slipping
    0.93
     slipped
    0.91
     fringes
    0.89
     slip
    0.87
     slips
    0.85
     interstices
    0.81
     borderline
    0.81
     gaps
    0.80
    Activations Density 0.014%

    No Known Activations