© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 169
    Prev
    Next
    INDEX
    Explanations

    starting response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     акку
    0.53
     grim
    0.51
    णार
    0.50
     पीड़िता
    0.49
    ্লি
    0.49
     pulsating
    0.49
    俏
    0.49
     현
    0.48
     stesso
    0.48
    頹
    0.47
    POSITIVE LOGITS
     overheard
    0.55
    िक्स
    0.52
    Mapped
    0.52
    機会
    0.52
    械
    0.51
     ance
    0.50
     stolen
    0.50
    хам
    0.50
     slide
    0.49
    cedence
    0.49
    Activations Density 0.004%

    No Known Activations