© 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. 6502
    Prev
    Next
    INDEX
    Explanations

    spots are

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

    effects, saving, felt, minute

    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
     none
    0.48
     vždy
    0.45
     也
    0.44
     lots
    0.43
    也
    0.43
     longest
    0.42
     throughout
    0.41
     vše
    0.41
     cual
    0.40
     всегда
    0.40
    POSITIVE LOGITS
     роман
    0.49
    стный
    0.47
     অথবা
    0.47
    거나
    0.47
     உடனடியாக
    0.46
    Expression
    0.46
    瀟
    0.45
    诙
    0.45
    俏
    0.44
     দ্রুত
    0.44
    Activations Density 0.000%

    No Known Activations