© 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-65K
    7. 8012
    Prev
    Next
    INDEX
    Explanations

    mountains and their features

    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_65k_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
     liquides
    0.53
     superfluid
    0.50
     incubated
    0.48
     líquidos
    0.48
     Integrative
    0.47
     metabolites
    0.47
    泳
    0.46
     rectangles
    0.46
     neutrophils
    0.46
     Algebras
    0.45
    POSITIVE LOGITS
     mountain
    1.41
    mountain
    1.23
    山
    1.23
    Mountain
    1.23
     mountains
    1.20
     Mountain
    1.15
    ⛰
    1.15
     পর্বত
    1.05
     hill
    1.05
    山的
    1.03
    Activations Density 0.100%

    No Known Activations