© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11287
    Prev
    Next
    INDEX
    Explanations

    email subject lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agencia
    0.38
    Kisi
    0.37
    फ़ी
    0.37
     institución
    0.37
     公式
    0.37
    étés
    0.36
     após
    0.36
    ᚖ
    0.36
     संस्थान
    0.35
    clamp
    0.35
    POSITIVE LOGITS
     subject
    1.59
    Subject
    1.59
     Subject
    1.51
    subject
    1.48
    SUBJECT
    1.39
     SUBJECT
    1.36
     सब्जेक्ट
    1.31
     subiect
    1.20
     sujet
    1.13
     subjects
    1.11
    Activations Density 0.060%

    No Known Activations