© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36396
    Prev
    Next
    INDEX
    Explanations

    performance and ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    家庭
    0.51
     измене
    0.51
     глоба
    0.48
     metamorphosis
    0.47
    倫
    0.46
     శరీర
    0.45
    性を
    0.45
    上昇
    0.44
     изменение
    0.44
    螫
    0.44
    POSITIVE LOGITS
     your
    0.64
     but
    0.51
     ваших
    0.50
     Bob
    0.48
     Commercial
    0.47
     Salmon
    0.47
     Before
    0.47
     Amaz
    0.46
     Rocket
    0.46
     oil
    0.46
    Activations Density 0.028%

    No Known Activations