© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 9287
    Prev
    Next
    INDEX
    Explanations

    aircraft components and related concepts

    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
    тся
    1.48
    呤
    1.20
    ষুধ
    1.17
    ről
    1.13
    ्र
    1.08
    ়
    1.06
    tted
    1.04
    de
    1.03
    haired
    1.03
    itäten
    1.02
    POSITIVE LOGITS
    ের
    1.53
    ین
    1.30
    ת
    1.30
    ات
    1.19
    s
    1.19
     także
    1.18
     jugador
    1.18
     væ
    1.17
    Aluno
    1.17
     resultat
    1.16
    Activations Density 0.026%

    No Known Activations