© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54701
    Prev
    Next
    INDEX
    Explanations

    sides, no, prol, loved, resolved, goal

    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
    После
    0.48
    Rates
    0.47
    Avec
    0.47
    type
    0.45
    Prison
    0.45
    Deb
    0.44
    Clause
    0.44
    不
    0.44
    With
    0.44
    後
    0.44
    POSITIVE LOGITS
     mammals
    0.49
     skiing
    0.49
     weld
    0.49
     picnic
    0.48
     backpacking
    0.48
     relocation
    0.48
     congruent
    0.47
     introvert
    0.47
     welds
    0.47
     disprove
    0.47
    Activations Density 0.002%

    No Known Activations