© 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. 26518
    Prev
    Next
    INDEX
    Explanations

    segmenst, written, intended, system, severity, FM

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

    abstract thought, self-awareness

    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
     Elaina
    0.57
    ക്കേണ്ട
    0.55
     appuy
    0.49
     Secondo
    0.49
     Hinweise
    0.49
    ৰ
    0.48
    ⃙
    0.48
     kiuj
    0.48
     paragraphe
    0.46
    liquer
    0.46
    POSITIVE LOGITS
    J
    0.46
    AN
    0.45
    OMO
    0.45
    WY
    0.43
    P
    0.43
    AT
    0.42
    Helen
    0.42
    PIC
    0.42
    U
    0.42
    Ѡ
    0.42
    Activations Density 0.000%

    No Known Activations