© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 9227
    Prev
    Next
    INDEX
    Explanations

    from the perspective of

    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
    परेशन
    0.61
     bananas
    0.59
    ela
    0.57
    _
    0.56
    𝚜
    0.55
     dreams
    0.54
     scenery
    0.54
    的机会
    0.54
    ography
    0.54
     yells
    0.53
    POSITIVE LOGITS
     liturgical
    0.63
    Ṣ
    0.61
    Astr
    0.60
     evidentiary
    0.59
    ENTAL
    0.58
     уж
    0.57
    ETIC
    0.57
    ologisk
    0.57
     मद्देनजर
    0.57
    ERNAL
    0.57
    Activations Density 0.002%

    No Known Activations