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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12612
    Prev
    Next
    INDEX
    Explanations

    LinkedIn profile URL

    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
     fandom
    0.44
    皇帝
    0.41
    াকারী
    0.40
     antice
    0.40
    eros
    0.38
    Pyro
    0.37
    洳
    0.37
     "\(
    0.37
     huevos
    0.37
    ʬ
    0.37
    POSITIVE LOGITS
     LinkedIn
    2.89
    LinkedIn
    2.77
     linkedin
    2.53
     Linkedin
    2.52
    linkedin
    2.34
    Linkedin
    2.30
     Linked
    1.51
    Linked
    1.35
     लिं
    1.34
     linked
    1.07
    Activations Density 0.017%

    No Known Activations