© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50102
    Prev
    Next
    INDEX
    Explanations

    core concepts and structures

    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_40_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
    ზი
    0.43
    ակի
    0.40
    றிந்த
    0.38
    वाल
    0.38
    phosphorylation
    0.38
     circon
    0.36
    ઓ
    0.36
    esus
    0.36
    هان
    0.35
    🤯
    0.35
    POSITIVE LOGITS
     वेर
    0.45
    ूम
    0.42
    㚣
    0.40
     portions
    0.39
     various
    0.38
    ë
    0.38
     boundaries
    0.37
     различ
    0.36
     พื้น
    0.36
     snacks
    0.36
    Activations Density 0.002%

    No Known Activations