© 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. 87382
    Prev
    Next
    INDEX
    Explanations

    connectivity and services

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

    video resolution

    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
    gradient
    0.48
    adjust
    0.45
     autoc
    0.44
    date
    0.43
    learn
    0.42
     abelian
    0.42
     $+$
    0.41
     readjust
    0.41
    linear
    0.41
    alkyl
    0.41
    POSITIVE LOGITS
    மர்
    0.45
    📔
    0.45
    را
    0.45
    ياً
    0.45
    琦
    0.44
     ممل
    0.43
     décerné
    0.43
    lovepoetry
    0.43
    膀
    0.43
    راً
    0.43
    Activations Density 0.000%

    No Known Activations