© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36983
    Prev
    Next
    INDEX
    Explanations

    healing recovery

    np_acts-logits-general · gemini-2.5-flash-lite

    collapsing and exhausted states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ходження
    0.40
    Ⲓ
    0.39
     príp
    0.38
     inap
    0.38
    ビング
    0.38
    BLACKLIST
    0.38
    ล็อก
    0.38
    ᴱ
    0.38
    𝓛
    0.38
    YELLOW
    0.37
    POSITIVE LOGITS
     recover
    0.83
     recovers
    0.76
     recovery
    0.75
     recovering
    0.73
     recoveries
    0.70
     recovered
    0.69
    recovery
    0.68
     recuper
    0.68
     recuperación
    0.68
     survivors
    0.67
    Activations Density 0.028%

    No Known Activations