© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169082
    Prev
    Next
    INDEX
    Explanations

    quiet + noun

    np_acts-logits-general · gemini-2.5-flash-lite

    quiet descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     }{}_{\
    0.55
     TouchUtils
    0.45
    </h5>
    0.44
     problémy
    0.44
     toNumber
    0.44
     consegue
    0.42
     অতঃপর
    0.42
    </th>
    0.42
     !_
    0.42
     stycz
    0.41
    POSITIVE LOGITS
     comfortable
    0.54
     confortable
    0.50
    rard
    0.49
    seiten
    0.48
    comfortable
    0.48
     confidently
    0.46
    confident
    0.46
    ولد
    0.46
    जर
    0.46
     comfortably
    0.46
    Activations Density 0.018%

    No Known Activations