© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142907
    Prev
    Next
    INDEX
    Explanations

    material properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    п
    0.53
    驃
    0.50
     ра
    0.49
    Ко
    0.49
    Про
    0.49
    Л
    0.47
    Ар
    0.47
    He
    0.47
    Primero
    0.47
    Ре
    0.45
    POSITIVE LOGITS
    et
    0.50
     πάντα
    0.50
     Moments
    0.47
     时
    0.47
     မှ
    0.47
    untamento
    0.46
    itatis
    0.45
    olarmente
    0.45
    és
    0.45
     nostra
    0.45
    Activations Density 0.000%

    No Known Activations