© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43921
    Prev
    Next
    INDEX
    Explanations

    ceiling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     действия
    0.83
     стены
    0.82
    ني
    0.80
     étend
    0.80
    طيع
    0.80
    𝒔
    0.80
     дороги
    0.79
     массы
    0.79
     темы
    0.78
    ي
    0.78
    POSITIVE LOGITS
    ok
    1.09
    il
    1.07
    ol
    1.05
    ag
    1.01
    p
    0.96
    OP
    0.92
    ur
    0.89
    per
    0.87
    an
    0.86
    ad
    0.86
    Activations Density 0.001%

    No Known Activations