© 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. 199642
    Prev
    Next
    INDEX
    Explanations

    lists of items or quantities

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

    actions, requests, and communications

    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
     идентифика
    0.50
    銀行
    0.48
     मित्रता
    0.48
    谿
    0.48
    Ultr
    0.46
     нацыяна
    0.45
    自動
    0.45
    擲
    0.45
    ु
    0.45
    sonar
    0.44
    POSITIVE LOGITS
     starved
    0.44
     이날
    0.44
     cura
    0.42
     oppressed
    0.42
     Markdown
    0.42
     üzerinde
    0.41
     Atmos
    0.41
    FromThe
    0.41
     देखील
    0.40
     coloro
    0.40
    Activations Density 0.000%

    No Known Activations