© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    AI emotional expression and suggestion

    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
     jeder
    1.38
     regl
    1.36
     fiecare
    1.35
     potere
    1.35
    icos
    1.34
     Ogni
    1.32
     Każ
    1.29
    卽
    1.29
    ialize
    1.28
     regol
    1.28
    POSITIVE LOGITS
     suggesting
    1.38
     seemed
    1.33
     suggests
    1.21
    美味し
    1.20
     suggest
    1.18
     apologized
    1.18
     indeed
    1.16
     apologised
    1.15
     piqu
    1.15
    Haha
    1.15
    Activations Density 0.086%

    No Known Activations