© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 121081
    Prev
    Next
    INDEX
    Explanations

    determiner followed by noun/verb

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

    horizontal, added by, checking advanced

    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
    ່
    0.44
    體
    0.43
     pneum
    0.43
     Ärzte
    0.43
     dove
    0.43
    Co
    0.43
     टू
    0.43
     bottle
    0.42
    थे
    0.42
    Prim
    0.42
    POSITIVE LOGITS
    шинство
    0.45
     যোগ
    0.44
    .');
    0.44
     reunir
    0.43
     なら
    0.42
    akkhati
    0.41
     -*-
    0.41
    badbreak
    0.41
     -"
    0.40
    gather
    0.40
    Activations Density 0.000%

    No Known Activations