© 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-262K
    7. 8178
    Prev
    Next
    INDEX
    Explanations

    describing specific instances

    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_262k_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
    GameObject
    0.40
     tubers
    0.40
    HexString
    0.40
    Contact
    0.38
    міну
    0.38
    Voltage
    0.37
     rodziny
    0.37
    ຣ
    0.36
    リエステル
    0.35
    灸
    0.35
    POSITIVE LOGITS
    simply
    0.49
     clarity
    0.46
    that
    0.45
    comple
    0.45
    เพื่อให้
    0.43
    intention
    0.43
     தெளி
    0.42
     anlaş
    0.42
     don
    0.41
     Simply
    0.41
    Activations Density 0.001%

    No Known Activations