© 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-262K
    7. 13634
    Prev
    Next
    INDEX
    Explanations

    non-english words and characters

    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_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
    <0xE3>
    0.38
     mieć
    0.37
     exist
    0.37
    benius
    0.37
     traumat
    0.36
     onward
    0.36
    frequency
    0.35
    イク
    0.34
    mathrm
    0.34
    ///////////////
    0.34
    POSITIVE LOGITS
     және
    0.49
     ఉపయోగ
    0.45
     γεγον
    0.44
    ລິ
    0.44
    मूर्ति
    0.43
    بلغ
    0.42
    केन
    0.42
    秭
    0.41
     եւ
    0.41
     և
    0.40
    Activations Density 0.007%

    No Known Activations