© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17433
    Prev
    Next
    INDEX
    Explanations

    reducing costs and expectations

    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_16_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
    การ
    1.30
     оружи
    1.25
    يد
    1.23
     ingreso
    1.23
    ق
    1.20
    ط
    1.20
    ה
    1.20
    لي
    1.17
    时间
    1.16
    高
    1.16
    POSITIVE LOGITS
    V
    1.21
    F
    1.17
    Lower
    1.16
    N
    1.15
    diameter
    1.12
    elling
    1.10
    erian
    1.09
    T
    1.09
    I
    1.09
    esy
    1.07
    Activations Density 0.022%

    No Known Activations