© 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. 45023
    Prev
    Next
    INDEX
    Explanations

    technical details and descriptions

    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
    Gregor
    0.45
     Doors
    0.43
    )}_
    0.40
    ം
    0.40
    rosse
    0.39
     Gone
    0.39
     coles
    0.39
     Lil
    0.38
     When
    0.38
     नगर
    0.38
    POSITIVE LOGITS
     totaling
    0.59
     totalling
    0.49
     amounting
    0.40
    ánchez
    0.39
    يًا
    0.38
    chatbot
    0.38
     participating
    0.37
    enamefont
    0.36
    🫠
    0.36
     tận
    0.36
    Activations Density 0.003%

    No Known Activations