© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3969
    Prev
    Next
    INDEX
    Explanations

    hunting and animal activities

    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
    TWI
    0.75
     Electrode
    0.74
     Electrochemical
    0.74
    lava
    0.74
     lava
    0.73
    冪
    0.72
     মঙ্গল
    0.70
     Magenta
    0.70
    偈
    0.70
     Amitabh
    0.69
    POSITIVE LOGITS
     hunting
    3.64
     hunters
    3.42
     hunter
    3.29
     Hunting
    3.28
     hunt
    3.27
    hunting
    3.14
     hunts
    3.10
    Hunting
    3.06
     hunted
    2.93
     Hunters
    2.92
    Activations Density 0.100%

    No Known Activations