© 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. 41957
    Prev
    Next
    INDEX
    Explanations

    use Face ID, Touch ID, passcode

    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
    зак
    0.45
     பா
    0.41
     ска
    0.41
     зак
    0.39
     prepar
    0.39
     環
    0.38
    ly
    0.37
    }$$
    0.37
    }")
    0.37
     및
    0.36
    POSITIVE LOGITS
    蛩
    0.55
     quelli
    0.55
     sekarang
    0.54
     peny
    0.52
     ceux
    0.52
    त्ति
    0.50
    Estos
    0.50
    廾
    0.50
    цыю
    0.49
     hasilnya
    0.49
    Activations Density 0.005%

    No Known Activations