© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168749
    Prev
    Next
    INDEX
    Explanations

    using analogies

    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_31_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
     $
    0.51
    on
    0.50
     Used
    0.49
    S
    0.47
    text
    0.47
     Therapy
    0.46
     large
    0.46
     used
    0.45
    wood
    0.45
     school
    0.45
    POSITIVE LOGITS
    ﭜ
    0.55
     actualizaciones
    0.53
     ولو
    0.51
    гій
    0.50
     estadísticas
    0.49
    Downward
    0.49
     disgraceful
    0.49
     modificaciones
    0.49
     alterações
    0.49
     поча
    0.48
    Activations Density 0.008%

    No Known Activations