© 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. 53-GEMMASCOPE-2-RES-262K
    7. 8947
    Prev
    Next
    INDEX
    Explanations

    signs and identifiers

    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_53_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
    螂
    0.43
     வட்ட
    0.40
    溇
    0.40
    枺
    0.38
    縷
    0.37
    걸
    0.37
    勮
    0.36
    ̀u
    0.35
    ্ডি
    0.34
    ំប
    0.34
    POSITIVE LOGITS
     sign
    4.16
     Sign
    3.98
    Sign
    3.94
    sign
    3.75
     signing
    3.75
     signed
    3.59
     SIGN
    3.58
     Signing
    3.41
    Signing
    3.36
    SIGN
    3.33
    Activations Density 0.119%

    No Known Activations