© 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. 238519
    Prev
    Next
    INDEX
    Explanations

    following specific words

    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
    ValMap
    0.55
    levelname
    0.54
    TimeDict
    0.49
    direita
    0.48
    ຖື
    0.48
    dte
    0.48
    𒇻
    0.48
     முஸ்
    0.47
    nombre
    0.46
     اړه
    0.45
    POSITIVE LOGITS
     accelerating
    0.55
     surfacing
    0.52
     by
    0.51
     accelerates
    0.49
    無
    0.49
     anima
    0.47
    К
    0.47
     chains
    0.46
    小
    0.46
     amplification
    0.45
    Activations Density 0.001%

    No Known Activations