© 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. 110429
    Prev
    Next
    INDEX
    Explanations

    Generally accepted, arguably, focus

    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
     유
    0.49
     Basis
    0.44
    っぽ
    0.43
     thông
    0.42
     증
    0.41
     Brew
    0.41
     Ú
    0.40
     Nú
    0.40
     Mort
    0.40
     Observations
    0.40
    POSITIVE LOGITS
    km
    0.49
    asp
    0.49
    izens
    0.48
    ⺠
    0.48
    ritic
    0.45
     ترقی
    0.44
     vegetal
    0.43
    kas
    0.43
    ricorn
    0.43
     mainstream
    0.42
    Activations Density 0.011%

    No Known Activations