© 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. 143851
    Prev
    Next
    INDEX
    Explanations

    greek primordial deities

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

    origins of poetry and myth

    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
    राबाद
    0.43
    माष्टमी
    0.42
    ﮯ
    0.42
    izante
    0.41
     expositions
    0.41
     जोकि
    0.41
     бушлай
    0.40
     মসজি
    0.40
    नामेंट
    0.40
     normed
    0.40
    POSITIVE LOGITS
     Ε
    0.48
    Utt
    0.47
    cret
    0.47
    Hyd
    0.46
    கரு
    0.46
     Ut
    0.45
     Er
    0.45
     Cory
    0.44
    Ut
    0.44
    Ty
    0.44
    Activations Density 0.018%

    No Known Activations