© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    unethical content or specific eras

    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
    rinsic
    2.78
    7
    2.71
    8
    2.45
    6
    2.24
     makeSound
    2.22
    9
    2.22
    لاك
    2.17
    5
    2.13
    LICENSE
    2.12
    3
    2.10
    POSITIVE LOGITS
    Organisation
    2.29
     organisation
    2.28
     Organisation
    2.12
     historians
    2.10
     arrows
    2.10
     leaks
    2.08
     diarrhoea
    2.08
    デイ
    2.07
     lược
    2.05
    ouncement
    1.98
    Activations Density 0.021%

    No Known Activations