© 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. 70000
    Prev
    Next
    INDEX
    Explanations

    who works or is

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

    look around, something raw, visible mechanism

    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
     respondió
    0.50
    }".
    0.46
     طور
    0.46
     Uk
    0.44
     இது
    0.43
     fluct
    0.43
     Astana
    0.43
    }.
    0.43
     پاسخ
    0.42
     Duel
    0.42
    POSITIVE LOGITS
     SLA
    0.51
     specialists
    0.46
    방법
    0.45
    اء
    0.44
     RES
    0.44
    সেন
    0.43
    이자
    0.42
    CLUDE
    0.41
    फ़
    0.41
    센
    0.40
    Activations Density 0.001%

    No Known Activations