© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15828
    Prev
    Next
    INDEX
    Explanations

    alternate reality or negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    '
    1.20
    ination
    0.86
    ining
    0.82
     '
    0.81
    acy
    0.79
    O
    0.79
    Ofer
    0.77
    P
    0.75
    '/
    0.74
    ove
    0.73
    POSITIVE LOGITS
    ದ್ದರಿಂದ
    0.91
     BLUEN
    0.86
    𝒇
    0.82
     exemptions
    0.81
     conséquences
    0.79
     Deutsches
    0.77
     photospheres
    0.77
     scones
    0.77
    𝚁
    0.76
     Elmer
    0.76
    Activations Density 0.000%

    No Known Activations