© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2380
    Prev
    Next
    INDEX
    Explanations

    technical tool and service names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    دانلود
    0.78
     j
    0.69
     neither
    0.67
      
    0.63
     handful
    0.62
     Neither
    0.62
     pr
    0.56
     whether
    0.56
     almost
    0.56
     _
    0.55
    POSITIVE LOGITS
    Wise
    1.23
    Mate
    1.22
    zilla
    1.21
    Lab
    1.20
    Scape
    1.18
    Guru
    1.13
    Hub
    1.13
    Hero
    1.12
    Flow
    1.12
    Sense
    1.12
    Activations Density 0.551%

    No Known Activations