© 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. 211231
    Prev
    Next
    INDEX
    Explanations

    Capitol, feasible, trouble, state, excerpt

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

    extraterrestrial origin

    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
    ക്കള്‍
    0.52
     смогут
    0.47
     ネックレス
    0.45
    杢
    0.43
    AMI
    0.42
    ক্সি
    0.42
    RECT
    0.41
    þ
    0.41
    ाइस
    0.41
     находятся
    0.41
    POSITIVE LOGITS
    appart
    0.45
     extrait
    0.41
     was
    0.41
     Dev
    0.40
    ˂
    0.40
     Enh
    0.40
     Freiheit
    0.39
     excerpt
    0.39
     mencionó
    0.39
     Krak
    0.39
    Activations Density 0.000%

    No Known Activations