© 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. 175398
    Prev
    Next
    INDEX
    Explanations

    amazing photo confidence

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

    parties in agreements

    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
    㑯
    0.46
    雬
    0.44
    adina
    0.44
    μία
    0.42
     früher
    0.42
    Eres
    0.42
    elda
    0.41
    ifting
    0.41
    altra
    0.41
     لص
    0.41
    POSITIVE LOGITS
    ログ
    0.47
     comienzan
    0.46
     logra
    0.46
    ឍ
    0.46
    團
    0.44
     existem
    0.44
     pravidel
    0.44
     yw
    0.43
     また
    0.43
     temps
    0.42
    Activations Density 0.001%

    No Known Activations