© 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. 40-GEMMASCOPE-2-RES-262K
    7. 165066
    Prev
    Next
    INDEX
    Explanations

    filtration and explicit saving

    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_40_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
    ⵅ
    0.45
    Baz
    0.43
    rologist
    0.39
     Wynne
    0.38
    퐫
    0.38
     Claude
    0.37
     база
    0.37
    ᖕ
    0.37
    铄
    0.37
    ('@
    0.36
    POSITIVE LOGITS
    ichlor
    0.42
     depleted
    0.41
     aged
    0.41
     Aged
    0.41
     úlo
    0.40
     ageing
    0.40
     yoghurt
    0.40
     sắc
    0.39
     electrop
    0.39
     responde
    0.39
    Activations Density 0.001%

    No Known Activations