© 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. 164432
    Prev
    Next
    INDEX
    Explanations

    your followed by possessive nouns

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

    clause deals with Unsupervised, Retargeting, DPCM

    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
    .
    0.48
     peroxidase
    0.45
     цве
    0.45
     часов
    0.45
    posals
    0.45
     slaughtered
    0.45
     equipments
    0.45
     laps
    0.44
    er
    0.44
     penicillin
    0.44
    POSITIVE LOGITS
     costit
    0.55
     সাংগঠনিক
    0.48
    ONEDB
    0.47
    셸
    0.47
     costitu
    0.47
     된
    0.46
    cció
    0.46
    톄
    0.45
    しまう
    0.45
     constitué
    0.45
    Activations Density 0.001%

    No Known Activations