© 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. 222756
    Prev
    Next
    INDEX
    Explanations

    Cloud platform

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

    so far

    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
    beqz
    0.45
     těch
    0.44
    apanam
    0.43
    اءِ
    0.42
    ط
    0.41
     numeral
    0.40
     holster
    0.40
    েশনে
    0.40
    钳
    0.39
     tijdens
    0.39
    POSITIVE LOGITS
    PhysRev
    0.47
    DAM
    0.46
    賴
    0.46
    NaHCO
    0.45
    ื
    0.43
    ולה
    0.43
    ESO
    0.43
    Biographie
    0.42
    呉
    0.42
    unpublished
    0.42
    Activations Density 0.001%

    No Known Activations