© 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. 59699
    Prev
    Next
    INDEX
    Explanations

    qualities and states

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

    to be able to

    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
     буквы
    0.51
    䔋
    0.48
    Oscar
    0.47
     yüzde
    0.46
     🌱
    0.46
     açúcar
    0.46
    㭂
    0.45
     açık
    0.44
     chữ
    0.44
    葛
    0.44
    POSITIVE LOGITS
    uo
    0.51
    provides
    0.49
    rom
    0.47
    vey
    0.47
     notoriously
    0.46
     possessing
    0.46
    lay
    0.45
    wit
    0.45
    ce
    0.44
    allows
    0.44
    Activations Density 0.000%

    No Known Activations