© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45075
    Prev
    Next
    INDEX
    Explanations

    Individual autonomy, access, privacy, freedom, scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ن
    0.47
     Produkt
    0.46
    ب
    0.46
     produkt
    0.44
    Produkt
    0.43
    QCD
    0.43
    Geschichte
    0.43
     সর্বপ্রথম
    0.43
    REN
    0.42
    TECHN
    0.42
    POSITIVE LOGITS
     unacceptable
    0.48
     sorely
    0.46
    owała
    0.46
    oted
    0.46
    ovane
    0.45
    kelig
    0.45
    ⓡ
    0.45
    ίζουν
    0.43
    acje
    0.43
    iyati
    0.43
    Activations Density 0.003%

    No Known Activations