© 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-16K
    7. 9258
    Prev
    Next
    INDEX
    Explanations

    time decay, erosion, term, value

    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_16k_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
    ро
    0.76
    ان
    0.76
    RE
    0.74
    enciones
    0.73
    ニ
    0.73
    ӗ
    0.71
    ленные
    0.71
    یو
    0.70
    োরের
    0.70
    ে
    0.70
    POSITIVE LOGITS
     QoS
    0.95
     Oman
    0.94
     Brom
    0.89
     Bruxelles
    0.82
     molto
    0.81
     molte
    0.81
     Japon
    0.80
     Johannes
    0.80
     Bless
    0.80
     :)
    0.80
    Activations Density 0.001%

    No Known Activations