© 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. 112382
    Prev
    Next
    INDEX
    Explanations

    lists of items and locations

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

    two distinct, different, immediate, wavelengths

    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
     ومد
    0.45
     navigated
    0.45
     قرارد
    0.43
     اختیار
    0.42
     جسم
    0.42
     فرزند
    0.42
     هند
    0.41
     균
    0.41
     mérid
    0.40
     축
    0.40
    POSITIVE LOGITS
    uk
    0.51
    0
    0.51
    ifa
    0.51
    ua
    0.50
    ques
    0.48
    ৭০
    0.48
    zip
    0.47
    ip
    0.46
    nome
    0.46
    il
    0.46
    Activations Density 0.000%

    No Known Activations