© 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. 12-GEMMASCOPE-2-RES-262K
    7. 35432
    Prev
    Next
    INDEX
    Explanations

    not sure, limited, false

    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_12_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
    ﻊ
    0.89
    ovala
    0.83
    чное
    0.82
    ovali
    0.81
     Бы
    0.79
     повышения
    0.79
     откло
    0.79
    𝗿
    0.79
    ypen
    0.78
    itake
    0.78
    POSITIVE LOGITS
     المثلث
    0.80
    }))
    0.77
     Sherry
    0.77
     relatives
    0.74
     autres
    0.73
     alternatives
    0.73
     اش
    0.71
    ']))
    0.70
     TEMPERATURE
    0.68
     towns
    0.67
    Activations Density 0.000%

    No Known Activations