© 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. 39132
    Prev
    Next
    INDEX
    Explanations

    2. followed by text

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

    Report for

    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
    瑋
    0.50
    ੴ
    0.48
    땅
    0.48
    م
    0.46
     inwards
    0.45
     appreciate
    0.44
    ц
    0.44
    Ти
    0.43
    Ấ
    0.43
    엄
    0.42
    POSITIVE LOGITS
    simmons
    0.47
    orescence
    0.45
    ent
    0.44
    oxa
    0.42
    estr
    0.41
     सिराज
    0.41
    veless
    0.40
    ores
    0.39
     বৃহত্তর
    0.39
    ᓛ
    0.39
    Activations Density 0.000%

    No Known Activations