© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3277
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency or character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻢ
    0.21
     corals
    0.21
     dimerization
    0.20
     aigus
    0.20
     mineralization
    0.20
     monotonicity
    0.20
     رجسٹ
    0.20
     glycolysis
    0.19
     aerodynamics
    0.19
     pierres
    0.19
    POSITIVE LOGITS
    -
    0.26
    un
    0.24
    ated
    0.24
    en
    0.24
    x
    0.24
    í
    0.24
    i
    0.23
    ata
    0.22
    ati
    0.22
    ec
    0.22
    Activations Density 0.998%

    No Known Activations