© 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. 144961
    Prev
    Next
    INDEX
    Explanations

    specific phrases

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

    specific contexts and qualifiers

    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
    ledged
    0.42
    Projeto
    0.42
    GetHeight
    0.42
    ദ്ധതി
    0.41
    Ϣ
    0.41
     بقت
    0.40
    projeto
    0.40
    Tabuleiro
    0.39
    }$
    0.39
     قطع
    0.39
    POSITIVE LOGITS
     Higgs
    0.45
     ally
    0.43
     Hobart
    0.43
     Straits
    0.42
    フェア
    0.42
     hann
    0.42
     Fairfax
    0.41
     लास्ट
    0.41
     Manoj
    0.41
     HE
    0.40
    Activations Density 0.001%

    No Known Activations