© 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. 44483
    Prev
    Next
    INDEX
    Explanations

    intensified adjectives or adverbs

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

    intensifiers followed by adjectives

    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
     INSTITUTE
    0.50
     आत्मनिर्भर
    0.48
     that
    0.47
     항상
    0.46
     आश्वासन
    0.46
     цих
    0.45
    "@
    0.44
     इंस्टीट्यूट
    0.43
    Specificity
    0.43
     कैलाश
    0.43
    POSITIVE LOGITS
     oppure
    0.47
     odnosno
    0.44
     erreurs
    0.43
     vezes
    0.42
     czyli
    0.41
     dwie
    0.41
    м
    0.40
    __))
    0.40
    деть
    0.40
     preuves
    0.40
    Activations Density 0.010%

    No Known Activations