© 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. 150900
    Prev
    Next
    INDEX
    Explanations

    refers to, should serve, keep an

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

    high precision threshold

    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
     カル
    0.52
    ينا
    0.49
     書い
    0.49
    texto
    0.49
    汚
    0.49
     ሽፋ
    0.48
    anni
    0.48
     腰
    0.48
    捐
    0.47
    namefont
    0.47
    POSITIVE LOGITS
     single
    0.71
     serious
    0.61
     paradise
    0.60
     noise
    0.57
     advanced
    0.56
     voltage
    0.55
     guessing
    0.55
     good
    0.55
     Single
    0.55
     fantasy
    0.55
    Activations Density 0.000%

    No Known Activations