© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4169
    Prev
    Next
    INDEX
    Explanations

    barely audible speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ucht
    1.61
    toon
    1.60
    x
    1.55
    uchte
    1.52
    znej
    1.52
     displeasure
    1.51
     خير
    1.47
    zn
    1.42
    portions
    1.42
    qed
    1.41
    POSITIVE LOGITS
     conj
    1.02
     parag
    0.99
    penet
    0.98
     Munro
    0.98
     campa
    0.93
    にか
    0.92
     THOM
    0.92
    磵
    0.92
     Surv
    0.91
    CMAKE
    0.91
    Activations Density 0.019%

    No Known Activations