© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    illegal substance or presence

    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
    เตรียม
    1.23
    brechen
    1.22
     persiapan
    1.16
    트를
    1.15
    itement
    1.15
    트에
    1.10
    购
    1.08
     لڑکی
    1.08
     apuestas
    1.06
    愆
    1.06
    POSITIVE LOGITS
    的存在
    1.89
     presence
    1.82
    presence
    1.67
     présence
    1.63
     presenza
    1.63
     존재
    1.62
     omnip
    1.61
     aanwezig
    1.61
     figura
    1.61
     Presence
    1.58
    Activations Density 0.246%

    No Known Activations