© 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. 62391
    Prev
    Next
    INDEX
    Explanations

    Jack Mod, spend time, sunset parade

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

    past solutions or refusals

    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
     przys
    0.44
    备
    0.44
    いろいろ
    0.42
    。。
    0.42
     Hermitian
    0.42
     Student
    0.41
    一般
    0.41
    时刻
    0.40
     maintain
    0.40
     Pregnancy
    0.40
    POSITIVE LOGITS
    檸
    0.50
    кна
    0.49
    losti
    0.48
    gangenheit
    0.48
     озеро
    0.48
    buatan
    0.47
     refraction
    0.47
     solubilities
    0.46
     озера
    0.46
     submerged
    0.45
    Activations Density 0.000%

    No Known Activations