© 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. 210700
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    technical documentation and programming

    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
     gerais
    0.51
    轲
    0.51
    عر
    0.49
    स्कार
    0.49
     билет
    0.48
    halb
    0.46
    ﻦ
    0.46
     GEAR
    0.46
    곧
    0.46
    kého
    0.46
    POSITIVE LOGITS
    akah
    0.50
    avana
    0.50
     沒有
    0.50
    ikti
    0.48
    ى
    0.47
    versible
    0.45
    artista
    0.45
     शकत
    0.43
    evin
    0.43
    視頻
    0.43
    Activations Density 0.000%

    No Known Activations