© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    job hashtags and career terms

    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
    ếu
    0.38
    Thể
    0.37
     chcete
    0.37
     Quinta
    0.36
    膚
    0.36
    નની
    0.36
    esse
    0.35
     肌
    0.35
     체
    0.35
    Baş
    0.35
    POSITIVE LOGITS
     Indeed
    0.52
     IJ
    0.49
    Indeed
    0.49
     indeed
    0.48
     IND
    0.44
    indeed
    0.43
     LI
    0.42
     JN
    0.42
    მართ
    0.41
     HJ
    0.41
    Activations Density 0.001%

    No Known Activations