© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21452
    Prev
    Next
    INDEX
    Explanations

    time to double

    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_40_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
     math
    0.44
     approximation
    0.41
     resTmp
    0.41
    実際の
    0.41
    複雑
    0.40
    údio
    0.40
     AppMethodBeat
    0.40
    ->__
    0.40
    렜
    0.39
    Routing
    0.39
    POSITIVE LOGITS
     vacations
    0.40
     putative
    0.39
     입
    0.38
    purge
    0.38
    }$\\
    0.37
     बांग
    0.37
    ोषित
    0.37
     subscribing
    0.37
    시간
    0.36
    ∮
    0.36
    Activations Density 0.000%

    No Known Activations