© 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. 53-GEMMASCOPE-2-RES-262K
    7. 48302
    Prev
    Next
    INDEX
    Explanations

    use descriptive names

    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_53_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
     necesaria
    0.46
     szükséges
    0.45
     necessaria
    0.43
     necessária
    0.42
     gereken
    0.41
     красивая
    0.41
     }*/
    0.41
     definición
    0.41
     weatherproof
    0.41
    িনে
    0.40
    POSITIVE LOGITS
     descriptive
    0.79
     camel
    0.77
     "_"
    0.71
     Descriptive
    0.71
    Camel
    0.69
    驼
    0.67
     naming
    0.66
     Camel
    0.66
    命名
    0.66
    camel
    0.65
    Activations Density 0.044%

    No Known Activations