© 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. 15949
    Prev
    Next
    INDEX
    Explanations

    relative clauses and conjunctions

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

    introducing rankings or difficulty levels

    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
     लौटे
    0.42
    —“
    0.42
    ඳ
    0.42
    *,
    0.40
     (“
    0.39
    <u>
    0.37
     بدء
    0.37
    苓
    0.36
    semble
    0.35
     područ
    0.35
    POSITIVE LOGITS
     котором
    0.57
     якому
    0.56
    avoir
    0.52
    which
    0.49
     ktorý
    0.49
    क्योंकि
    0.49
     เพราะ
    0.49
     который
    0.48
     którym
    0.48
     който
    0.48
    Activations Density 0.028%

    No Known Activations