© 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. 117627
    Prev
    Next
    INDEX
    Explanations

    apostille or Montessori reference

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

    types of things

    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
    jednoc
    0.55
    mapSize
    0.45
    భా
    0.45
    кле
    0.44
    defini
    0.43
    𒊕
    0.42
     மத
    0.42
    clientWidth
    0.42
     CLLocation
    0.41
    🏥
    0.41
    POSITIVE LOGITS
     indors
    0.49
     benefit
    0.49
     accords
    0.49
     unwarrant
    0.48
     officers
    0.48
     existencia
    0.48
     emotions
    0.48
     specifications
    0.47
     receipts
    0.46
     theorems
    0.46
    Activations Density 0.000%

    No Known Activations