© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10210
    Prev
    Next
    INDEX
    Explanations

    taking the lead

    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
    K
    2.02
    ک
    1.60
    к
    1.42
    К
    1.42
     êtres
    1.32
    կ
    1.31
    activiti
    1.30
    е
    1.30
    ר
    1.30
    ka
    1.27
    POSITIVE LOGITS
     digitar
    1.35
     esquina
    1.30
    囹
    1.30
    ция
    1.26
     Didier
    1.25
    INER
    1.22
    ния
    1.20
     subscripts
    1.20
     segar
    1.19
     mudar
    1.18
    Activations Density 0.006%

    No Known Activations