© 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. 60420
    Prev
    Next
    INDEX
    Explanations

    future of

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

    Early number, website, and situation contexts

    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
    毆
    0.49
    無視
    0.47
     resul
    0.47
    ﻹ
    0.44
    pett
    0.44
     पीड़िता
    0.43
    Pete
    0.43
    ールド
    0.43
     elektromagnet
    0.43
    䨋
    0.43
    POSITIVE LOGITS
     Technology
    0.48
     Fine
    0.47
     Mortgage
    0.47
     озе
    0.44
     Hiring
    0.42
     Fort
    0.42
    oir
    0.42
     Naf
    0.42
    ObjectClass
    0.41
     Conjug
    0.41
    Activations Density 0.000%

    No Known Activations