© 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. 208323
    Prev
    Next
    INDEX
    Explanations

    review later

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

    inbound rules, marketing teams, researchers who

    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
    deux
    0.52
    ढ़
    0.51
     novembro
    0.50
    蠔
    0.49
    ാണ
    0.49
    鳶
    0.47
     योगदान
    0.47
     noviembre
    0.47
    एन
    0.45
    उथ
    0.45
    POSITIVE LOGITS
     articulation
    0.54
     match
    0.47
     all
    0.47
    m
    0.46
     zippers
    0.45
     plates
    0.45
     досто
    0.45
     inception
    0.43
     incoming
    0.43
     caveats
    0.43
    Activations Density 0.001%

    No Known Activations