© 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. 3156
    Prev
    Next
    INDEX
    Explanations

    strong emotional states

    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
    !
    1.65
    !»
    1.65
    !\
    1.64
    ..!
    1.64
    !“
    1.63
    ...!
    1.63
    !".
    1.61
    !",
    1.61
    !";
    1.60
    !"
    1.60
    POSITIVE LOGITS
     fucking
    1.03
    Yeah
    0.96
     fucked
    0.95
     Yeah
    0.93
    においては
    0.88
    Fuck
    0.84
     fuck
    0.82
    に関しては
    0.80
     באופן
    0.79
     Fuck
    0.78
    Activations Density 0.048%

    No Known Activations