© 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. 105939
    Prev
    Next
    INDEX
    Explanations

    assertions and declarations

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

    prism, cells, goals, pairs, cuántica

    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
     konuda
    0.52
     vengeance
    0.49
     言
    0.48
     compon
    0.46
    ULE
    0.46
    ICKEL
    0.45
     contentious
    0.45
     blasp
    0.45
     जागा
    0.45
     sustenance
    0.44
    POSITIVE LOGITS
    aus
    0.49
    guests
    0.47
    ahue
    0.47
    omotor
    0.47
    ঞ্জাম
    0.47
    Mat
    0.46
     hoteles
    0.46
    E
    0.46
     Mat
    0.45
     hotels
    0.44
    Activations Density 0.001%

    No Known Activations