© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76195
    Prev
    Next
    INDEX
    Explanations

    celebrity height and fish

    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
    }$-(
    0.46
    }",
    0.44
    רת
    0.44
     абсолютно
    0.44
    Су
    0.43
    }((
    0.43
     Су
    0.43
    }".
    0.43
    ój
    0.42
    AllFilesIn
    0.42
    POSITIVE LOGITS
     microphones
    0.44
     yogurt
    0.41
     microwaves
    0.41
     screwdriver
    0.40
     veterinarian
    0.39
     midwives
    0.39
     mickey
    0.38
    ==
    0.38
     nursing
    0.38
     mentors
    0.38
    Activations Density 0.001%

    No Known Activations