© 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. 175325
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and consequences

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

    to the danger

    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
    '],$
    0.47
    EEP
    0.43
    ocolate
    0.43
    чено
    0.43
     ਹੀ
    0.43
    dasarkan
    0.42
    LoopBlend
    0.42
    ágoras
    0.42
    勐
    0.42
    נה
    0.42
    POSITIVE LOGITS
     for
    0.58
     Calf
    0.55
     his
    0.54
     we
    0.53
     applications
    0.52
     patience
    0.52
     Asian
    0.52
     our
    0.52
     focused
    0.50
     South
    0.50
    Activations Density 0.001%

    No Known Activations