© 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. 137078
    Prev
    Next
    INDEX
    Explanations

    queen song

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

    language specific terms

    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
     submer
    0.55
    の
    0.54
     ఫ
    0.53
    だけの
    0.53
    </i>
    0.52
     giữa
    0.50
     ရ
    0.50
     给
    0.50
    نی
    0.49
     进行
    0.49
    POSITIVE LOGITS
    anum
    0.49
    ઋ
    0.45
    Africa
    0.44
    spolit
    0.44
    टीशन
    0.43
     नागल
    0.42
    AIRMAN
    0.42
    Returns
    0.42
    rarse
    0.42
     Inheritance
    0.40
    Activations Density 0.000%

    No Known Activations