© 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. 14485
    Prev
    Next
    INDEX
    Explanations

    alternative + [noun]

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

    alternative uses and options

    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
    อย่างไร
    0.54
    લ
    0.54
    ה
    0.53
     equipe
    0.52
    И
    0.52
    ร้าย
    0.51
    گ
    0.51
    ס
    0.50
     ออก
    0.50
    lar
    0.49
    POSITIVE LOGITS
     Alternative
    1.26
    Alternative
    1.23
     alternative
    1.22
    alternative
    1.21
     альтерна
    1.20
     alternatif
    1.20
     Alternate
    1.13
     alterna
    1.13
    alternate
    1.08
     alternativ
    1.08
    Activations Density 0.026%

    No Known Activations