© 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. 32513
    Prev
    Next
    INDEX
    Explanations

    spatial reasoning and mapping

    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
    ܠ
    0.46
    파
    0.45
    X
    0.43
     stains
    0.42
    𝚕
    0.42
    ጺ
    0.42
     रामानंद
    0.41
    othesis
    0.41
    炲
    0.41
    orescent
    0.40
    POSITIVE LOGITS
     ذمہ
    0.50
     précédente
    0.48
    犄
    0.48
     Arbeiten
    0.47
     ampio
    0.46
    இதில்
    0.46
     Tahun
    0.45
     BadRequest
    0.45
     czym
    0.44
     توضیح
    0.44
    Activations Density 0.004%

    No Known Activations