© 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. 52657
    Prev
    Next
    INDEX
    Explanations

    lists, sequences, and clauses

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

    harmful ideologies and accessibility

    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
    נו
    0.52
     Pigeon
    0.50
    שת
    0.50
    メソッド
    0.46
     homestead
    0.46
    上がり
    0.45
    تی
    0.44
    山
    0.44
    Upper
    0.44
    Engineer
    0.44
    POSITIVE LOGITS
     `>`,
    0.47
    os
    0.46
     तेज़
    0.46
     devemos
    0.44
     podemos
    0.43
     Beziehungen
    0.43
     ჩვენ
    0.43
    essive
    0.43
     Dirichlet
    0.42
     वंचित
    0.42
    Activations Density 0.000%

    No Known Activations