© 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. 73789
    Prev
    Next
    INDEX
    Explanations

    home owners or remaining air

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

    Lost civilizations, building, nail, throat, available

    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
     ಬದಲ
    0.49
    ⓡ
    0.48
    <0x80>
    0.46
    f
    0.45
    ²)
    0.44
     CHANGE
    0.43
    に変更
    0.43
     cambio
    0.43
     cambi
    0.43
     從
    0.42
    POSITIVE LOGITS
    ية
    0.45
     ڈھاکہ
    0.45
    illeurs
    0.44
    Specular
    0.43
    acji
    0.42
     შეს
    0.42
    ników
    0.42
    ตาม
    0.41
    него
    0.41
     specular
    0.41
    Activations Density 0.000%

    No Known Activations