© 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. 10498
    Prev
    Next
    INDEX
    Explanations

    ambiguity and possibilities

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

    distinct choices or possibilities

    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
    🚛
    0.55
    ěstí
    0.54
    োপুরি
    0.52
    躹
    0.51
    🚚
    0.50
    越し
    0.49
    ড্রিম
    0.48
    ོ
    0.48
    🏦
    0.47
    θος
    0.47
    POSITIVE LOGITS
     possible
    0.64
     ambiguity
    0.63
     ambiguous
    0.62
     unambiguously
    0.61
     ambiguities
    0.61
     ambigu
    0.59
     possibilities
    0.57
     unambiguous
    0.57
    可能有
    0.56
     there
    0.54
    Activations Density 0.022%

    No Known Activations