© 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. 81630
    Prev
    Next
    INDEX
    Explanations

    classic Chianti

    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
     lisää
    0.51
    indole
    0.44
     groei
    0.44
    ite
    0.43
    inity
    0.42
     cabo
    0.41
    ী
    0.41
    ീ
    0.41
     الا
    0.41
    same
    0.41
    POSITIVE LOGITS
    ಿಯನ್
    0.46
     heavily
    0.45
     superhuman
    0.45
     Dayan
    0.45
     Canary
    0.44
     harshly
    0.44
     bravely
    0.44
     canonical
    0.43
     populares
    0.43
     Canonical
    0.43
    Activations Density 0.009%

    No Known Activations