© 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. 221759
    Prev
    Next
    INDEX
    Explanations

    Ramaphosa, accumulated over

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

    multilingual explanations and examples

    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
    ’,
    0.52
    ak
    0.51
    ’
    0.51
    ann
    0.48
    ın
    0.47
     or
    0.46
    emailer
    0.45
    -
    0.45
    AK
    0.44
    AN
    0.43
    POSITIVE LOGITS
    WeakTable
    0.55
     제곱
    0.55
     apparten
    0.52
    Ց
    0.51
     있었습니다
    0.50
     vínculos
    0.50
    렸
    0.50
     вирі
    0.49
    СТИ
    0.49
     intrav
    0.49
    Activations Density 0.000%

    No Known Activations