© 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-16K
    7. 1116
    Prev
    Next
    INDEX
    Explanations

    closing html tags

    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_16k_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
     misused
    1.34
     Callum
    1.27
     llaman
    1.25
    韮
    1.22
     روسی
    1.22
     scream
    1.21
     unauthorised
    1.21
    attiv
    1.19
    ovington
    1.19
     cheeky
    1.17
    POSITIVE LOGITS
    </body>
    1.10
    ตะ
    1.08
    gh
    1.07
    hor
    1.05
     Hor
    1.05
    Hor
    1.02
    <!--
    1.02
    gher
    1.01
    hum
    1.01
    </footer>
    1.00
    Activations Density 0.109%

    No Known Activations