© 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. 47747
    Prev
    Next
    INDEX
    Explanations

    Comparison of detail levels

    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
    √(
    0.48
    aks
    0.44
    anned
    0.42
    ukkan
    0.41
    ok
    0.41
    ʊ
    0.41
     $
    0.40
    uk
    0.40
     $_{
    0.40
    joen
    0.40
    POSITIVE LOGITS
     altres
    0.45
     priprav
    0.45
     Amongst
    0.44
     Inici
    0.43
     naszym
    0.42
     dla
    0.42
    ということで
    0.42
    平时
    0.42
     Posteriormente
    0.41
     Depuis
    0.41
    Activations Density 0.002%

    No Known Activations