© 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. 4822
    Prev
    Next
    INDEX
    Explanations

    adult story

    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
    サイズの
    1.64
    bentuk
    1.62
    pués
    1.61
    sized
    1.58
    SIZ
    1.54
    dden
    1.51
    愆
    1.50
    QSpacerItem
    1.49
    娌
    1.49
    rictor
    1.47
    POSITIVE LOGITS
    Diffuse
    1.54
    ation
    1.46
     Cincinnati
    1.40
     Navarra
    1.40
    undo
    1.40
     동작
    1.38
     Martina
    1.37
    8
    1.37
    ado
    1.34
    ados
    1.33
    Activations Density 0.059%

    No Known Activations