© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4196
    Prev
    Next
    INDEX
    Explanations

    description lists, bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    济
    1.95
    urious
    1.91
    わた
    1.80
    貽
    1.80
     exposes
    1.79
     erros
    1.79
     culprit
    1.77
    浚
    1.77
     conclusiones
    1.76
     explains
    1.75
    POSITIVE LOGITS
    же
    1.19
    voice
    1.17
     стату
    1.17
    род
    1.16
     приблизи
    1.12
     NPC
    1.11
     singular
    1.08
    名字
    1.08
     حسب
    1.06
    初始
    1.05
    Activations Density 0.004%

    No Known Activations