© 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. 50495
    Prev
    Next
    INDEX
    Explanations

    social enterprise

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

    potential difference

    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
     receipts
    0.47
    に着
    0.44
     receitas
    0.44
     s
    0.43
     recip
    0.43
     Januar
    0.43
     into
    0.42
     Cent
    0.42
    ’
    0.42
     recevoir
    0.42
    POSITIVE LOGITS
    äng
    0.47
    嬸
    0.47
    luğu
    0.46
    miktar
    0.46
    counterx
    0.46
    Gosudarstvennyj
    0.46
    屶
    0.45
    icheskij
    0.45
    ulação
    0.45
    bedarf
    0.45
    Activations Density 0.000%

    No Known Activations