© 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. 51782
    Prev
    Next
    INDEX
    Explanations

    ICT planning

    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
    ස්ථ
    0.47
    ك
    0.46
    غ
    0.46
    كو
    0.45
    ر
    0.45
    .
    0.43
    ج
    0.43
    En
    0.43
     enak
    0.42
    }',
    0.42
    POSITIVE LOGITS
     MPEG
    0.49
    μπο
    0.47
    γγρα
    0.46
    ရှင်
    0.46
     Voltage
    0.46
    ekwondo
    0.45
    များနှင့်
    0.45
     MIDI
    0.45
     Solar
    0.44
     Military
    0.44
    Activations Density 0.002%

    No Known Activations