© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172111
    Prev
    Next
    INDEX
    Explanations

    screen root, full lot, no follow

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

    see section references

    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
    ainak
    0.51
    锼
    0.50
    ئيه
    0.47
    مع
    0.45
    هُ
    0.45
    苻
    0.45
     kia
    0.45
    みると
    0.45
    苹
    0.45
     نباش
    0.44
    POSITIVE LOGITS
    <0x8B>
    0.48
    slip
    0.46
    etheless
    0.46
    hed
    0.44
    ೊ
    0.44
     hardship
    0.44
    arrival
    0.44
    heds
    0.44
    nutrition
    0.43
     উল্লেখযোগ্য
    0.43
    Activations Density 0.000%

    No Known Activations