© 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. 157409
    Prev
    Next
    INDEX
    Explanations

    manufacturer declares intention

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

    files, circle, microorganisms

    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
     ofic
    0.59
     आईएएस
    0.47
    official
    0.46
     ඔ
    0.46
    opod
    0.44
     официа
    0.44
     oficial
    0.43
    १
    0.43
     paraît
    0.43
     hud
    0.43
    POSITIVE LOGITS
     धात
    0.44
     JY
    0.44
     fabricating
    0.42
    جب
    0.41
    鸠
    0.41
    队的
    0.41
    碎
    0.41
    بل
    0.40
     Fail
    0.40
     ভারতকে
    0.40
    Activations Density 0.000%

    No Known Activations