© 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. 70391
    Prev
    Next
    INDEX
    Explanations

    Nations, property, Update, 3M

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

    how much

    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
    নিবার
    0.52
    游客
    0.52
    Nigerian
    0.50
    гій
    0.49
    特朗普
    0.49
    клу
    0.47
    }]}\
    0.47
    〗
    0.46
    传媒
    0.46
    Tela
    0.46
    POSITIVE LOGITS
    ss
    0.51
     녹
    0.49
     /
    0.49
    d
    0.48
     veins
    0.47
    드
    0.47
     қар
    0.47
    v
    0.47
     hourglass
    0.47
    설
    0.46
    Activations Density 0.001%

    No Known Activations