© 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. 51078
    Prev
    Next
    INDEX
    Explanations

    anthropomorphic animals or technical security

    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
    🫦
    0.52
    हरियाणा
    0.49
    ☘
    0.48
     Bhi
    0.47
    🦟
    0.47
    Libs
    0.47
    েইলি
    0.46
    𝟭
    0.46
    <unused560>
    0.46
    <unused512>
    0.45
    POSITIVE LOGITS
     security
    0.49
     fixed
    0.47
     source
    0.45
     (
    0.43
     code
    0.43
     ridge
    0.43
     supplies
    0.42
     procur
    0.42
     rest
    0.41
     certified
    0.41
    Activations Density 0.012%

    No Known Activations