© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    Nebulae and system utilities

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

    fiber optic

    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
    soluble
    0.54
     llega
    0.52
    𝘇
    0.52
    𒋻
    0.51
    nętr
    0.50
    シーズン
    0.48
    Verlag
    0.48
    হেল
    0.48
    oxid
    0.48
    squre
    0.48
    POSITIVE LOGITS
     cláus
    0.44
    غيل
    0.43
     elk
    0.42
     DECL
    0.41
    ﺒ
    0.41
    بار
    0.41
    去了
    0.41
     وما
    0.40
    弈
    0.40
    一看
    0.40
    Activations Density 0.000%

    No Known Activations