© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    Friendly and helpful communication

    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
     femin
    1.16
     pilates
    1.12
    Gender
    1.06
     gender
    1.06
    rinsic
    1.06
    6
    1.02
    7
    1.02
    ekwondo
    1.01
    LICENSE
    1.00
     Gender
    0.98
    POSITIVE LOGITS
    日が
    1.42
    パン
    1.42
     tins
    1.37
    纍
    1.33
     suele
    1.30
     schrij
    1.30
    сро
    1.30
     disusun
    1.29
    dated
    1.29
     bung
    1.28
    Activations Density 0.039%

    No Known Activations