© 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. 40-GEMMASCOPE-2-RES-65K
    7. 52215
    Prev
    Next
    INDEX
    Explanations

    test steps expected result

    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_40_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
     fija
    0.42
    तिया
    0.41
    捜
    0.39
    ્યુ
    0.39
    Richardson
    0.38
     घ
    0.38
     వర
    0.38
    anesulfonyl
    0.36
     भु
    0.35
    可靠
    0.35
    POSITIVE LOGITS
    긔
    0.39
     FINE
    0.38
    픕
    0.38
     osmotic
    0.36
     TX
    0.36
    geri
    0.36
     fine
    0.35
    realm
    0.35
     REM
    0.35
     TW
    0.35
    Activations Density 0.004%

    No Known Activations