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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218725
    Prev
    Next
    INDEX
    Explanations

    family, your, world, Inc, Limits

    np_acts-logits-general · gemini-2.5-flash-lite

    distribution, discomfort, production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ว
    0.55
    น
    0.50
    క
    0.49
    ব
    0.49
    ن
    0.48
    Potato
    0.48
    گ
    0.48
    Damage
    0.47
    న
    0.47
    ه
    0.46
    POSITIVE LOGITS
     વ્યવ
    0.52
     فط
    0.49
     まま
    0.48
     vann
    0.46
     мень
    0.46
     فح
    0.46
    enciar
    0.45
     carre
    0.44
    lysninger
    0.44
     continental
    0.44
    Activations Density 0.000%

    No Known Activations