© 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. 55617
    Prev
    Next
    INDEX
    Explanations

    research and flexibility

    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
     slutt
    0.42
    मानुसार
    0.38
     inclinations
    0.37
    無
    0.37
     beliefs
    0.37
     無
    0.36
    向け
    0.36
     простых
    0.36
    𠃍
    0.36
     whoever
    0.36
    POSITIVE LOGITS
    aded
    0.45
    总部
    0.42
    klı
    0.42
    apeti
    0.41
    aked
    0.41
    EventRecorder
    0.41
    apag
    0.41
    ור
    0.40
    ichung
    0.40
    arj
    0.40
    Activations Density 0.001%

    No Known Activations