© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 11342
    Prev
    Next
    INDEX
    Explanations

    thanks and acknowledgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    i
    0.92
    tekn
    0.85
     digniss
    0.83
     liczb
    0.82
    Ich
    0.81
    tttt
    0.81
    ierten
    0.81
     ailes
    0.79
    ])),
    0.78
     cifra
    0.77
    POSITIVE LOGITS
    ័រ
    0.84
    ست
    0.78
     conspicuously
    0.78
    Բ
    0.78
    ڑک
    0.76
     Диа
    0.75
    سن
    0.75
     Defenders
    0.75
     questionable
    0.74
    ресень
    0.74
    Activations Density 0.000%

    No Known Activations