© 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. 133902
    Prev
    Next
    INDEX
    Explanations

    staff tomarketing teamrelied ongive them

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

    formal or specific contexts

    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
    4
    0.66
    annual
    0.58
    commentaire
    0.57
    seag
    0.57
    monthly
    0.55
    5
    0.55
    rv
    0.52
    0
    0.52
    3
    0.51
    your
    0.50
    POSITIVE LOGITS
    െയി
    0.48
    鎸
    0.47
     validInput
    0.45
    맥
    0.44
    बम
    0.42
     identifications
    0.41
    仃
    0.41
    लील
    0.40
    識別
    0.40
     Hew
    0.39
    Activations Density 0.000%

    No Known Activations