© 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. 104598
    Prev
    Next
    INDEX
    Explanations

    Deloitte's NPD Group

    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
    '
    1.00
    Eight
    0.65
    .
    0.62
    ’
    0.61
    amas
    0.59
    なります
    0.53
     Eight
    0.51
    Had
    0.51
    .'
    0.50
    aneous
    0.50
    POSITIVE LOGITS
    a
    0.76
    ه
    0.76
    सिस
    0.71
     ücretsiz
    0.67
    هي
    0.66
    tól
    0.65
     exorbit
    0.64
     número
    0.64
     serviço
    0.64
     apă
    0.64
    Activations Density 0.001%

    No Known Activations