© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170010
    Prev
    Next
    INDEX
    Explanations

    we know

    np_acts-logits-general · gemini-2.5-flash-lite

    professional contexts and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这场
    0.49
    环节
    0.45
     पैन
    0.45
     предпо
    0.43
    阳
    0.43
    סטי
    0.42
     పెద్ద
    0.42
    乐观
    0.42
    changers
    0.41
     되겠죠
    0.41
    POSITIVE LOGITS
    Ow
    0.52
    DZ
    0.48
    4
    0.46
    OU
    0.46
    :
    0.46
    Ori
    0.46
     siang
    0.45
    IR
    0.45
    اری
    0.45
     Blau
    0.44
    Activations Density 0.001%

    No Known Activations