© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11896
    Prev
    Next
    INDEX
    Explanations

    quantifier reduction or sentiment

    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
    er
    1.36
    मति
    1.28
     mutated
    1.24
    g
    1.21
    isation
    1.19
    o
    1.18
    itä
    1.15
    pdf
    1.14
    m
    1.14
    tym
    1.13
    POSITIVE LOGITS
    Standards
    1.67
     kiệm
    1.51
     Interval
    1.47
     оптима
    1.42
    STAND
    1.42
     STAND
    1.41
     química
    1.40
    Ladder
    1.38
    Standard
    1.37
     propel
    1.36
    Activations Density 0.000%

    No Known Activations