© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 217269
    Prev
    Next
    INDEX
    Explanations

    increase or drop

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

    phrases beginning sentences

    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
     src
    0.47
    ’
    0.47
    )
    0.45
     clipart
    0.43
     cama
    0.43
     `{
    0.43
     contest
    0.42
     meter
    0.42
     acceleration
    0.42
     audio
    0.41
    POSITIVE LOGITS
     පිළ
    0.55
     ಗೌ
    0.51
    unpriv
    0.49
    signOut
    0.49
    पूर्व
    0.49
    सामान्यीकृत
    0.48
     அவர்களை
    0.48
     нарушение
    0.48
    ஏ
    0.48
    तील
    0.47
    Activations Density 0.000%

    No Known Activations