© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15557
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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_13_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
    ва
    0.93
    แต
    0.88
    しろ
    0.86
    寬
    0.85
     любого
    0.85
    ien
    0.85
    ıc
    0.84
    пле
    0.84
     quello
    0.84
    ことも
    0.83
    POSITIVE LOGITS
    marvel
    1.29
     melodrama
    1.27
     marbles
    1.24
     hypotheses
    1.24
     explosions
    1.24
    <unused1169>
    1.21
     doctrines
    1.21
     motorsport
    1.21
     antioxidant
    1.20
     cranks
    1.20
    Activations Density 0.000%

    No Known Activations