© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 244222
    Prev
    Next
    INDEX
    Explanations

    other, alternatives

    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
    niveau
    0.52
    nivel
    0.51
    કારે
    0.50
    ᄌ
    0.48
    multilayer
    0.48
    ível
    0.47
    prepared
    0.46
    KERNEL
    0.46
    multiplier
    0.45
    ^{*}$-
    0.45
    POSITIVE LOGITS
     other
    0.53
     autres
    0.52
    ↵↵
    0.49
     Other
    0.46
     دیگر
    0.44
    棣
    0.44
     arbitr
    0.43
     سایر
    0.43
     attribu
    0.42
     accuse
    0.42
    Activations Density 0.001%

    No Known Activations