© 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. 313
    Prev
    Next
    INDEX
    Explanations

    instruction to select the

    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
    ك
    1.57
    يد
    1.38
    ن
    1.38
    ני
    1.23
    री
    1.23
     océ
    1.18
    つ
    1.16
    ون
    1.16
    },
    1.12
     ແລະ
    1.11
    POSITIVE LOGITS
    t
    1.43
    де
    1.41
    u
    1.40
    。
    1.30
    ।
    1.30
    times
    1.29
    d
    1.28
    speed
    1.27
    dır
    1.27
    sons
    1.24
    Activations Density 0.033%

    No Known Activations