© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28699
    Prev
    Next
    INDEX
    Explanations

    Arena, popularISER, Lord, pet

    np_acts-logits-general · gemini-2.5-flash-lite

    Convert to pandas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    クリル
    0.44
    ‌تر
    0.43
    denoted
    0.42
    kenn
    0.42
    \|^
    0.41
     يمكنك
    0.41
     කොට
    0.40
    թ
    0.40
    kte
    0.40
    पूर्वी
    0.40
    POSITIVE LOGITS
     in
    0.51
     সদ্য
    0.50
     Nikola
    0.48
     Arm
    0.48
     Amar
    0.47
     আখ
    0.47
     Nix
    0.46
     Clos
    0.46
     Aqu
    0.46
     Bone
    0.46
    Activations Density 0.000%

    No Known Activations