© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43498
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to, based on

    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
     Б
    0.48
     राजधानी
    0.47
    ધી
    0.46
    杝
    0.45
    થી
    0.45
     ब्र
    0.45
    bitro
    0.45
     बाकी
    0.44
     спокойно
    0.44
    B
    0.43
    POSITIVE LOGITS
     phytochemical
    0.52
     oprac
    0.48
     epigen
    0.46
     piante
    0.46
     uzn
    0.46
     inferred
    0.45
     Noetherian
    0.45
     femora
    0.45
     académ
    0.44
     pptn
    0.44
    Activations Density 0.004%

    No Known Activations