© 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. 156274
    Prev
    Next
    INDEX
    Explanations

    part of everyday speech

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

    wishing well greetings

    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
     erzählt
    0.58
    Andreas
    0.53
    َة
    0.53
    REW
    0.52
     saddo
    0.50
     przyjem
    0.49
     erzählen
    0.48
     Ingrid
    0.48
    ُمْ
    0.47
     obdob
    0.47
    POSITIVE LOGITS
    1
    0.48
    2
    0.45
     to
    0.45
    multipart
    0.42
    ocio
    0.42
    лось
    0.41
    tbody
    0.41
     trekking
    0.41
     රට
    0.41
     linguistics
    0.40
    Activations Density 0.000%

    No Known Activations