© 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. 50658
    Prev
    Next
    INDEX
    Explanations

    Medium, older systems, potential

    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
     iterations
    0.46
     대비
    0.46
     openness
    0.45
     analog
    0.45
    વે
    0.44
     analogue
    0.43
    対
    0.43
     օ
    0.41
    帔
    0.41
     covariates
    0.41
    POSITIVE LOGITS
    är
    0.51
    uque
    0.49
    y
    0.48
    вища
    0.48
    u
    0.47
     Medford
    0.47
     l
    0.47
    OO
    0.47
    il
    0.46
    EM
    0.46
    Activations Density 0.007%

    No Known Activations