© 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. 195628
    Prev
    Next
    INDEX
    Explanations

    America alone

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

    Transfer Learning Strategies

    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
    ém
    0.49
    outside
    0.47
     Its
    0.46
    versch
    0.45
    oblig
    0.44
     "../
    0.44
     Outside
    0.43
     보유
    0.43
    close
    0.43
    fr
    0.42
    POSITIVE LOGITS
    させた
    0.50
    ꯋ
    0.49
    ᑯ
    0.47
     Takashi
    0.46
    ᕈ
    0.45
     Suzy
    0.45
    脅
    0.45
     ferrite
    0.45
    리즈
    0.44
     வெப்சீரி
    0.44
    Activations Density 0.004%

    No Known Activations