© 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. 26921
    Prev
    Next
    INDEX
    Explanations

    specific details or instances

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

    certain circumstances

    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
    이지만
    0.46
     podcast
    0.45
    ও
    0.43
    ŏ
    0.43
     version
    0.43
     podcasts
    0.42
    檚
    0.42
    є
    0.41
     platforms
    0.40
    지만
    0.40
    POSITIVE LOGITS
     furent
    0.50
     besonderen
    0.44
     دادن
    0.44
    samples
    0.43
     युवकों
    0.43
     युवती
    0.43
    fdata
    0.42
     puzzled
    0.42
     seraient
    0.42
     Kindern
    0.41
    Activations Density 0.001%

    No Known Activations