© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2376
    Prev
    Next
    INDEX
    Explanations

    positive phrasing and supportive connection

    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
     membut
    1.54
     including
    1.44
    遭
    1.43
     visualizar
    1.43
     whether
    1.43
     necesitaba
    1.42
     moderation
    1.40
    のため
    1.38
    同期
    1.37
     undangan
    1.37
    POSITIVE LOGITS
     vào
    1.49
    together
    1.25
    र्ख
    1.23
    طان
    1.19
    MBT
    1.17
    コル
    1.17
    یف
    1.16
    켓
    1.16
    парат
    1.15
     together
    1.15
    Activations Density 0.026%

    No Known Activations