© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29559
    Prev
    Next
    INDEX
    Explanations

    singlish

    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_40_width_262k_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
     Designed
    0.42
    ంక
    0.41
     estimados
    0.40
     Estimates
    0.39
     Gathering
    0.39
    礴
    0.39
     Homeless
    0.38
    酊
    0.38
     Guests
    0.38
    閒
    0.38
    POSITIVE LOGITS
    Sing
    0.61
     SING
    0.59
     sing
    0.57
     Sing
    0.53
    SING
    0.51
    apore
    0.49
     singlet
    0.49
    sing
    0.47
     노래
    0.44
    along
    0.44
    Activations Density 0.003%

    No Known Activations