© 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-262K
    7. 145865
    Prev
    Next
    INDEX
    Explanations

    bottle caps, Studio Paint, Free Zone

    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_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
    ibal
    0.76
    azón
    0.70
     asesinato
    0.67
    詷
    0.66
    archiwizowane
    0.63
     McKay
    0.62
    臓
    0.62
    ihar
    0.60
    䛛
    0.60
     aprobación
    0.60
    POSITIVE LOGITS
    STO
    0.79
     Tw
    0.76
     meets
    0.72
    ི
    0.67
     denied
    0.67
     सेवक
    0.66
    Tw
    0.65
    廂
    0.65
     kant
    0.65
     reve
    0.64
    Activations Density 0.003%

    No Known Activations