© 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. 19797
    Prev
    Next
    INDEX
    Explanations

    http://

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

    song lyrics

    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
    ダイニング
    0.46
    ﾓ
    0.40
    子が
    0.39
    ริง
    0.38
    かかる
    0.38
    జు
    0.38
    หม
    0.37
    oplankton
    0.37
    ਯ
    0.37
    袢
    0.37
    POSITIVE LOGITS
     energy
    0.50
     as
    0.48
     in
    0.47
     energi
    0.46
     energie
    0.45
     !,
    0.44
     enerji
    0.43
     hit
    0.42
     discover
    0.42
     Hit
    0.42
    Activations Density 0.000%

    No Known Activations