© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10238
    Prev
    Next
    INDEX
    Explanations

    time, padding, word, input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Zweifel
    2.19
     justifications
    1.92
     frankly
    1.85
     persönlich
    1.84
    ष्टाचार
    1.83
    ﻢ
    1.83
     部分
    1.82
    实例化
    1.80
     justification
    1.78
     Verantwortung
    1.76
    POSITIVE LOGITS
    j
    1.37
    ificio
    1.36
    Super
    1.36
    sh
    1.33
     उन्ह
    1.33
    枠
    1.32
    sl
    1.32
    mans
    1.30
    u
    1.30
    賓
    1.29
    Activations Density 0.000%

    No Known Activations