© 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. 53145
    Prev
    Next
    INDEX
    Explanations

    Ks, of, only, seeking, online, country

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

    certain quality

    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
     subsided
    0.45
     humiliated
    0.45
     cracked
    0.44
    אנ
    0.44
     ⋮
    0.43
    দেখিতে
    0.43
     scooped
    0.43
     stabbed
    0.42
     tapped
    0.42
     ಘ
    0.42
    POSITIVE LOGITS
    َق
    0.49
    exerc
    0.45
    KILL
    0.44
     comunica
    0.43
     investimentos
    0.43
     territ
    0.43
     Italien
    0.43
    燡
    0.43
     によ
    0.42
    Exerc
    0.42
    Activations Density 0.000%

    No Known Activations