© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3017
    Prev
    Next
    INDEX
    Explanations

    checking software version

    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
    Not in Any Lists

    No Comments

    Negative Logits
    На
    1.73
    Duration
    1.66
    ته
    1.60
    Обра
    1.59
    تها
    1.58
    ſh
    1.56
    При
    1.55
    ଼
    1.54
    derd
    1.53
    та
    1.51
    POSITIVE LOGITS
     पद्धतीने
    2.05
     최대한
    1.95
    igil
    1.94
     공격
    1.88
     다양
    1.83
     계속
    1.82
    <0x8E>
    1.82
    norms
    1.82
     확
    1.82
     최고
    1.81
    Activations Density 0.004%

    No Known Activations